Showing 1–37 of 37 results for author: Ahmed, O

Semantic Risk Scoring of Aggregated Metrics: An AI-Driven Approach for Healthcare Data Governance

Authors: Mohammed Omer Shakeel Ahmed

Abstract: Large healthcare institutions typically operate multiple business intelligence (BI) teams segmented by domain, including clinical performance, fundraising, operations, and compliance. Due to HIPAA, FERPA, and IRB restrictions, these teams face challenges in sharing patient-level data needed for analytics. To mitigate this, A metric aggregation table is proposed, which is a precomputed, privacy-com… ▽ More Large healthcare institutions typically operate multiple business intelligence (BI) teams segmented by domain, including clinical performance, fundraising, operations, and compliance. Due to HIPAA, FERPA, and IRB restrictions, these teams face challenges in sharing patient-level data needed for analytics. To mitigate this, A metric aggregation table is proposed, which is a precomputed, privacy-compliant summary. These abstractions enable decision-making without direct access to sensitive data. However, even aggregated metrics can inadvertently lead to privacy risks if constructed without rigorous safeguards. A modular AI framework is proposed that evaluates SQL-based metric definitions for potential overexposure using both semantic and syntactic features. Specifically, the system parses SQL queries into abstract syntax trees (ASTs), extracts sensitive patterns (e.g., fine-grained GROUP BY on ZIP code or gender), and encodes the logic using pretrained CodeBERT embeddings. These are fused with structural features and passed to an XGBoost classifier trained to assign risk scores. Queries that surpass the risk threshold (e.g., > 0.85) are flagged and returned with human-readable explanations. This enables proactive governance, preventing statistical disclosure before deployment. This implementation demonstrates strong potential for cross-departmental metric sharing in healthcare while maintaining compliance and auditability. The system also promotes role-based access control (RBAC), supports zero-trust data architectures, and aligns with national data modernization goals by ensuring that metric pipelines are explainable, privacy-preserving, and AI-auditable by design. Unlike prior works that rely on runtime data access to flag privacy violations, the proposed framework performs static, explainable detection at the query-level, enabling pre-execution protection and audit readiness △ Less

Submitted 8 March, 2026; originally announced March 2026.

Comments: 6 pages, 3 figures, 1 Table, Accepted for publication in the 21st Int. Conference on Data Science (ICDATA 25)

A Late-Fusion Multimodal AI Framework for Privacy-Preserving Deduplication in National Healthcare Data Environments

Authors: Mohammed Omer Shakeel Ahmed

Abstract: Duplicate records pose significant challenges in customer relationship management (CRM)and healthcare, often leading to inaccuracies in analytics, impaired user experiences, and compliance risks. Traditional deduplication methods rely heavily on direct identifiers such as names, emails, or Social Security Numbers (SSNs), making them ineffective under strict privacy regulations like GDPR and HIPAA,… ▽ More Duplicate records pose significant challenges in customer relationship management (CRM)and healthcare, often leading to inaccuracies in analytics, impaired user experiences, and compliance risks. Traditional deduplication methods rely heavily on direct identifiers such as names, emails, or Social Security Numbers (SSNs), making them ineffective under strict privacy regulations like GDPR and HIPAA, where such personally identifiable information (PII) is restricted or masked. In this research, I propose a novel, scalable, multimodal AI framework for detecting duplicates without depending on sensitive information. This system leverages three distinct modalities: semantic embeddings derived from textual fields (names, cities) using pre-trained DistilBERT models, behavioral patterns extracted from user login timestamps, and device metadata encoded through categorical embeddings. These heterogeneous modalities are combined using a late fusion approach and clustered via DBSCAN, an unsupervised density-based algorithm. This proposed model is evaluated against a traditional string-matching baseline on a synthetic CRM dataset specifically designed to reflect privacy-preserving constraints. The multimodal framework demonstrated good performance, achieving a good F1-score by effectively identifying duplicates despite variations and noise inherent in the data. This approach offers a privacy-compliant solution to entity resolution and supports secure digital infrastructure, enhances the reliability of public health analytics, and promotes ethical AI adoption across government and enterprise settings. It is well-suited for integration into national health data modernization efforts, aligning with broader goals of privacy-first innovation. △ Less

Submitted 4 March, 2026; originally announced March 2026.

Comments: 6 pages, 1 figure, 1 table. Accepted for publication in the 2025 IEEE International Conference on Future Machine Learning and Data Science (FMLDS)

Journal ref: 2025 IEEE International Conference on Future Machine Learning and Data Science (FMLDS)

Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?

Authors: Mir Rayat Imtiaz Hossain, Leo Feng, Leonid Sigal, Mohamed Osama Ahmed

Abstract: Large Language Models (LLMs) have emerged as promising recommendation systems, offering novel ways to model user preferences through generative approaches. However, many existing methods often rely solely on text semantics or incorporate collaborative signals in a limited manner, typically using only user or item embeddings. These methods struggle to handle multiple item embeddings representing us… ▽ More Large Language Models (LLMs) have emerged as promising recommendation systems, offering novel ways to model user preferences through generative approaches. However, many existing methods often rely solely on text semantics or incorporate collaborative signals in a limited manner, typically using only user or item embeddings. These methods struggle to handle multiple item embeddings representing user history, reverting to textual semantics and neglecting richer collaborative information. In this work, we propose a simple yet effective solution that projects user and item embeddings, learned from collaborative filtering, into the LLM token space via separate lightweight projector modules. A finetuned LLM then conditions on these projected embeddings alongside textual tokens to generate recommendations. Preliminary results show that this design effectively leverages structured user-item interaction data, improves recommendation performance over text-only LLM baselines, and offers a practical path for bridging traditional recommendation systems with modern LLMs. △ Less

Submitted 8 January, 2026; originally announced January 2026.

Comments: Presented in Multimodal Algorithmic Reasoning Workshop at NeurIPS 2025

Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning

Authors: NVIDIA, :, Mayank Mittal, Pascal Roth, James Tigue, Antoine Richard, Octi Zhang, Peter Du, Antonio Serrano-Muñoz, Xinjie Yao, René Zurbrügg, Nikita Rudin, Lukasz Wawrzyniak, Milad Rakhsha, Alain Denzler, Eric Heiden, Ales Borovicka, Ossama Ahmed, Iretiayo Akinola, Abrar Anwar, Mark T. Carlson, Ji Yuan Feng, Animesh Garg, Renato Gasoto, Lionel Gulich , et al. (82 additional authors not shown)

Abstract: We present Isaac Lab, the natural successor to Isaac Gym, which extends the paradigm of GPU-native robotics simulation into the era of large-scale multi-modal learning. Isaac Lab combines high-fidelity GPU parallel physics, photorealistic rendering, and a modular, composable architecture for designing environments and training robot policies. Beyond physics and rendering, the framework integrates… ▽ More We present Isaac Lab, the natural successor to Isaac Gym, which extends the paradigm of GPU-native robotics simulation into the era of large-scale multi-modal learning. Isaac Lab combines high-fidelity GPU parallel physics, photorealistic rendering, and a modular, composable architecture for designing environments and training robot policies. Beyond physics and rendering, the framework integrates actuator models, multi-frequency sensor simulation, data collection pipelines, and domain randomization tools, unifying best practices for reinforcement and imitation learning at scale within a single extensible platform. We highlight its application to a diverse set of challenges, including whole-body control, cross-embodiment mobility, contact-rich and dexterous manipulation, and the integration of human demonstrations for skill acquisition. Finally, we discuss upcoming integration with the differentiable, GPU-accelerated Newton physics engine, which promises new opportunities for scalable, data-efficient, and gradient-based approaches to robot learning. We believe Isaac Lab's combination of advanced simulation capabilities, rich sensing, and data-center scale execution will help unlock the next generation of breakthroughs in robotics research. △ Less

Submitted 6 November, 2025; originally announced November 2025.

Comments: Code and documentation are available here: https://github.com/isaac-sim/IsaacLab

Multivariate Time Series Forecasting with Gate-Based Quantum Reservoir Computing on NISQ Hardware

Authors: Wissal Hamhoum, Soumaya Cherkaoui, Jean-Frederic Laprade, Ola Ahmed, Shengrui Wang

Abstract: Quantum reservoir computing (QRC) offers a hardware-friendly approach to temporal learning, yet most studies target univariate signals and overlook near-term hardware constraints. This work introduces a gate-based QRC for multivariate time series (MTS-QRC) that pairs injection and memory qubits and uses a Trotterized nearest-neighbor transverse-field Ising evolution optimized for current device co… ▽ More Quantum reservoir computing (QRC) offers a hardware-friendly approach to temporal learning, yet most studies target univariate signals and overlook near-term hardware constraints. This work introduces a gate-based QRC for multivariate time series (MTS-QRC) that pairs injection and memory qubits and uses a Trotterized nearest-neighbor transverse-field Ising evolution optimized for current device connectivity and depth. On Lorenz-63 and ENSO, the method achieves a mean square error (MSE) of 0.0087 and 0.0036, respectively, performing on par with classical reservoir computing on Lorenz and above learned RNNs on both, while NVAR and clustered ESN remain stronger on some settings. On IBM Heron R2, MTS-QRC sustains accuracy with realistic depths and, interestingly, outperforms a noiseless simulator on ENSO; singular value analysis indicates that device noise can concentrate variance in feature directions, acting as an implicit regularizer for linear readout in this regime. These findings support the practicality of gate-based QRC for MTS forecasting on NISQ hardware and motivate systematic studies on when and how hardware noise benefits QRC readouts. △ Less

Submitted 15 October, 2025; originally announced October 2025.

Fingerprinting LLMs via Prompt Injection

Authors: Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li, Osama Ahmed, Zhicong Huang, Cheng Hong, Neil Gong

Abstract: Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one model is derived from another. Existing provenance detection methods have two main limitations: (1) they embed signals into the base model before release, which is infeasible for already published models, or (2) they compar… ▽ More Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one model is derived from another. Existing provenance detection methods have two main limitations: (1) they embed signals into the base model before release, which is infeasible for already published models, or (2) they compare outputs across models using hand-crafted or random prompts, which are not robust to post-processing. In this work, we propose LLMPrint, a novel detection framework that constructs fingerprints by exploiting LLMs' inherent vulnerability to prompt injection. Our key insight is that by optimizing fingerprint prompts to enforce consistent token preferences, we can obtain fingerprints that are both unique to the base model and robust to post-processing. We further develop a unified verification procedure that applies to both gray-box and black-box settings, with statistical guarantees. We evaluate LLMPrint on five base models and around 700 post-trained or quantized variants. Our results show that LLMPrint achieves high true positive rates while keeping false positive rates near zero. △ Less

Submitted 1 October, 2025; v1 submitted 29 September, 2025; originally announced September 2025.

Robust quantum reservoir computers for forecasting chaotic dynamics: generalized synchronization and stability

Authors: Osama Ahmed, Felix Tennie, Luca Magri

Abstract: We show that recurrent quantum reservoir computers (QRCs) and their recurrence-free architectures (RF-QRCs) are robust tools for learning and forecasting chaotic dynamics from time-series data. First, we formulate and interpret quantum reservoir computers as coupled dynamical systems, where the reservoir acts as a response system driven by training data; in other words, quantum reservoir computers… ▽ More We show that recurrent quantum reservoir computers (QRCs) and their recurrence-free architectures (RF-QRCs) are robust tools for learning and forecasting chaotic dynamics from time-series data. First, we formulate and interpret quantum reservoir computers as coupled dynamical systems, where the reservoir acts as a response system driven by training data; in other words, quantum reservoir computers are generalized-synchronization (GS) systems. Second, we show that quantum reservoir computers can learn chaotic dynamics and their invariant properties, such as Lyapunov spectra, attractor dimensions, and geometric properties such as the covariant Lyapunov vectors. This analysis is enabled by deriving the Jacobian of the quantum reservoir update. Third, by leveraging tools from generalized synchronization, we provide a method for designing robust quantum reservoir computers. We propose the criterion $GS=ESP$: GS implies the echo state property (ESP), and vice versa. We analytically show that RF-QRCs, by design, fulfill $GS=ESP$. Finally, we analyze the effect of simulated noise. We find that dissipation from noise enhances the robustness of quantum reservoir computers. Numerical verifications on systems of different dimensions support our conclusions. This work opens opportunities for designing robust quantum machines for chaotic time series forecasting on near-term quantum hardware. △ Less

Submitted 27 June, 2025; originally announced June 2025.

Comments: 28 pages, 12 figures

A Systematic Review of Open Datasets Used in Text-to-Image (T2I) Gen AI Model Safety

Authors: Rakeen Rouf, Trupti Bavalatti, Osama Ahmed, Dhaval Potdar, Faraz Jawed

Abstract: Novel research aimed at text-to-image (T2I) generative AI safety often relies on publicly available datasets for training and evaluation, making the quality and composition of these datasets crucial. This paper presents a comprehensive review of the key datasets used in the T2I research, detailing their collection methods, compositions, semantic and syntactic diversity of prompts and the quality,… ▽ More Novel research aimed at text-to-image (T2I) generative AI safety often relies on publicly available datasets for training and evaluation, making the quality and composition of these datasets crucial. This paper presents a comprehensive review of the key datasets used in the T2I research, detailing their collection methods, compositions, semantic and syntactic diversity of prompts and the quality, coverage, and distribution of harm types in the datasets. By highlighting the strengths and limitations of the datasets, this study enables researchers to find the most relevant datasets for a use case, critically assess the downstream impacts of their work given the dataset distribution, particularly regarding model safety and ethical considerations, and also identify the gaps in dataset coverage and quality that future research may address. △ Less

Submitted 22 February, 2025; originally announced March 2025.

Comments: Accepted for publication in IEEE Access, DOI: 10.1109/ACCESS.2025.3539933

Journal ref: IEEE Access 2025

Multi-objective Cat Swarm Optimization Algorithm based on a Grid System

Authors: Aram M. Ahmed, Bryar A. Hassan, Tarik A. Rashid, Kaniaw A. Noori, Soran Ab. M. Saeed, Omed H. Ahmed, Shahla U. Umar

Abstract: This paper presents a multi-objective version of the Cat Swarm Optimization Algorithm called the Grid-based Multi-objective Cat Swarm Optimization Algorithm (GMOCSO). Convergence and diversity preservation are the two main goals pursued by modern multi-objective algorithms to yield robust results. To achieve these goals, we first replace the roulette wheel method of the original CSO algorithm with… ▽ More This paper presents a multi-objective version of the Cat Swarm Optimization Algorithm called the Grid-based Multi-objective Cat Swarm Optimization Algorithm (GMOCSO). Convergence and diversity preservation are the two main goals pursued by modern multi-objective algorithms to yield robust results. To achieve these goals, we first replace the roulette wheel method of the original CSO algorithm with a greedy method. Then, two key concepts from Pareto Archived Evolution Strategy Algorithm (PAES) are adopted: the grid system and double archive strategy. Several test functions and a real-world scenario called the Pressure vessel design problem are used to evaluate the proposed algorithm's performance. In the experiment, the proposed algorithm is compared with other well-known algorithms using different metrics such as Reversed Generational Distance, Spacing metric, and Spread metric. The optimization results show the robustness of the proposed algorithm, and the results are further confirmed using statistical methods and graphs. Finally, conclusions and future directions were presented.. △ Less

Submitted 22 February, 2025; originally announced February 2025.

An Integrated Approach to Robotic Object Grasping and Manipulation

Authors: Owais Ahmed, M Huzaifa, M Areeb, Hamza Ali Khan

Abstract: In response to the growing challenges of manual labor and efficiency in warehouse operations, Amazon has embarked on a significant transformation by incorporating robotics to assist with various tasks. While a substantial number of robots have been successfully deployed for tasks such as item transportation within warehouses, the complex process of object picking from shelves remains a significant… ▽ More In response to the growing challenges of manual labor and efficiency in warehouse operations, Amazon has embarked on a significant transformation by incorporating robotics to assist with various tasks. While a substantial number of robots have been successfully deployed for tasks such as item transportation within warehouses, the complex process of object picking from shelves remains a significant challenge. This project addresses the issue by developing an innovative robotic system capable of autonomously fulfilling a simulated order by efficiently selecting specific items from shelves. A distinguishing feature of the proposed robotic system is its capacity to navigate the challenge of uncertain object positions within each bin of the shelf. The system is engineered to autonomously adapt its approach, employing strategies that enable it to efficiently locate and retrieve the desired items, even in the absence of pre-established knowledge about their placements. △ Less

Submitted 29 July, 2025; v1 submitted 20 November, 2024; originally announced November 2024.

Were RNNs All We Needed?

Authors: Leo Feng, Frederick Tung, Mohamed Osama Ahmed, Yoshua Bengio, Hossein Hajimirsadeghi

Abstract: The introduction of Transformers in 2017 reshaped the landscape of deep learning. Originally proposed for sequence modelling, Transformers have since achieved widespread success across various domains. However, the scalability limitations of Transformers - particularly with respect to sequence length - have sparked renewed interest in novel recurrent models that are parallelizable during training,… ▽ More The introduction of Transformers in 2017 reshaped the landscape of deep learning. Originally proposed for sequence modelling, Transformers have since achieved widespread success across various domains. However, the scalability limitations of Transformers - particularly with respect to sequence length - have sparked renewed interest in novel recurrent models that are parallelizable during training, offer comparable performance, and scale more effectively. In this work, we revisit sequence modelling from a historical perspective, focusing on Recurrent Neural Networks (RNNs), which dominated the field for two decades before the rise of Transformers. Specifically, we examine LSTMs (1997) and GRUs (2014). We demonstrate that by simplifying these models, we can derive minimal versions (minLSTMs and minGRUs) that (1) use fewer parameters than their traditional counterparts, (2) are fully parallelizable during training, and (3) achieve surprisingly competitive performance on a range of tasks, rivalling recent models including Transformers. △ Less

Submitted 28 November, 2024; v1 submitted 1 October, 2024; originally announced October 2024.

Optimal training of finitely-sampled quantum reservoir computers for forecasting of chaotic dynamics

Authors: Osama Ahmed, Felix Tennie, Luca Magri

Abstract: In the current Noisy Intermediate Scale Quantum (NISQ) era, the presence of noise deteriorates the performance of quantum computing algorithms. Quantum Reservoir Computing (QRC) is a type of Quantum Machine Learning algorithm, which, however, can benefit from different types of tuned noise. In this paper, we analyse the effect that finite-sampling noise has on the chaotic time-series prediction ca… ▽ More In the current Noisy Intermediate Scale Quantum (NISQ) era, the presence of noise deteriorates the performance of quantum computing algorithms. Quantum Reservoir Computing (QRC) is a type of Quantum Machine Learning algorithm, which, however, can benefit from different types of tuned noise. In this paper, we analyse the effect that finite-sampling noise has on the chaotic time-series prediction capabilities of QRC and Recurrence-free Quantum Reservoir Computing (RF-QRC). First, we show that, even without a recurrent loop, RF-QRC contains temporal information about previous reservoir states using leaky integrated neurons. This makes RF-QRC different from Quantum Extreme Learning Machines (QELM). Second, we show that finite sampling noise degrades the prediction capabilities of both QRC and RF-QRC while affecting QRC more due to the propagation of noise. Third, we optimize the training of the finite-sampled quantum reservoir computing framework using two methods: (a) Singular Value Decomposition (SVD) applied to the data matrix containing noisy reservoir activation states; and (b) data-filtering techniques to remove the high-frequencies from the noisy reservoir activation states. We show that denoising reservoir activation states improve the signal-to-noise ratios with smaller training loss. Finally, we demonstrate that the training and denoising of the noisy reservoir activation signals in RF-QRC are highly parallelizable on multiple Quantum Processing Units (QPUs) as compared to the QRC architecture with recurrent connections. The analyses are numerically showcased on prototypical chaotic dynamical systems with relevance to turbulence. This work opens opportunities for using quantum reservoir computing with finite samples for time-series forecasting on near-term quantum hardware. △ Less

Submitted 2 September, 2024; originally announced September 2024.

Comments: 11 pages, 14 figures

Attention as an RNN

Authors: Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Mohamed Osama Ahmed, Yoshua Bengio, Greg Mori

Abstract: The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of leveraging GPU parallelism. However, Transformers are computationally expensive at inference time, limiting their applications, particularly in low-resource settings (e.g., mobile and embedded devices). Addressing this, we (1) begin by showing that attention can… ▽ More The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of leveraging GPU parallelism. However, Transformers are computationally expensive at inference time, limiting their applications, particularly in low-resource settings (e.g., mobile and embedded devices). Addressing this, we (1) begin by showing that attention can be viewed as a special Recurrent Neural Network (RNN) with the ability to compute its \textit{many-to-one} RNN output efficiently. We then (2) show that popular attention-based models such as Transformers can be viewed as RNN variants. However, unlike traditional RNNs (e.g., LSTMs), these models cannot be updated efficiently with new tokens, an important property in sequence modelling. Tackling this, we (3) introduce a new efficient method of computing attention's \textit{many-to-many} RNN output based on the parallel prefix scan algorithm. Building on the new attention formulation, we (4) introduce \textbf{Aaren}, an attention-based module that can not only (i) be trained in parallel (like Transformers) but also (ii) be updated efficiently with new tokens, requiring only constant memory for inferences (like traditional RNNs). Empirically, we show Aarens achieve comparable performance to Transformers on $38$ datasets spread across four popular sequential problem settings: reinforcement learning, event forecasting, time series classification, and time series forecasting tasks while being more time and memory-efficient. △ Less

Submitted 28 May, 2024; v1 submitted 22 May, 2024; originally announced May 2024.

Taxonomic classification with maximal exact matches in KATKA kernels and minimizer digests

Authors: Dominika Draesslerová, Omar Ahmed, Travis Gagie, Jan Holub, Ben Langmead, Giovanni Manzini, Gonzalo Navarro

Abstract: For taxonomic classification, we are asked to index the genomes in a phylogenetic tree such that later, given a DNA read, we can quickly choose a small subtree likely to contain the genome from which that read was drawn. Although popular classifiers such as Kraken use $k$-mers, recent research indicates that using maximal exact matches (MEMs) can lead to better classifications. For example, we can… ▽ More For taxonomic classification, we are asked to index the genomes in a phylogenetic tree such that later, given a DNA read, we can quickly choose a small subtree likely to contain the genome from which that read was drawn. Although popular classifiers such as Kraken use $k$-mers, recent research indicates that using maximal exact matches (MEMs) can lead to better classifications. For example, we can build an augmented FM-index over the the genomes in the tree concatenated in left-to-right order; for each MEM in a read, find the interval in the suffix array containing the starting positions of that MEM's occurrences in those genomes; find the minimum and maximum values stored in that interval; take the lowest common ancestor (LCA) of the genomes containing the characters at those positions. This solution is practical, however, only when the total size of the genomes in the tree is fairly small. In this paper we consider applying the same solution to three lossily compressed representations of the genomes' concatenation: a KATKA kernel, which discards characters that are not in the first or last occurrence of any $k_{\max}$-tuple, for a parameter $k_{\max}$; a minimizer digest; a KATKA kernel of a minimizer digest. With a test dataset and these three representations of it, simulated reads and various parameter settings, we checked how many reads' longest MEMs occurred only in the sequences from which those reads were generated ("true positive" reads). For some parameter settings we achieved significant compression while only slightly decreasing the true-positive rate. △ Less

Submitted 4 April, 2024; v1 submitted 10 February, 2024; originally announced February 2024.

Adaptive Prognostic Malfunction Based Processor for Autonomous Landing Guidance Assistance System Using FPGA

Authors: Hossam O. Ahmed, David Wyatt

Abstract: The demand for more developed and agile urban taxi drones is increasing rapidly nowadays to sustain crowded cities and their traffic issues. The critical factor for spreading such technology could be related to the safety criteria that must be considered. One of the most critical safety aspects for such vertical and/or Short Take-Off and Landing (V/STOL) drones is related to safety during the land… ▽ More The demand for more developed and agile urban taxi drones is increasing rapidly nowadays to sustain crowded cities and their traffic issues. The critical factor for spreading such technology could be related to the safety criteria that must be considered. One of the most critical safety aspects for such vertical and/or Short Take-Off and Landing (V/STOL) drones is related to safety during the landing stage, in which most of the recent flight accidents have occurred. This paper focused on solving this issue by proposing decentralized processing cores that could improve the landing failure rate by depending on a Fuzzy Logic System (FLS) and additional Digital Signal Processing (DSP) elements. Also, the proposed system will enhance the safety factor during the landing stages by adding a self-awareness feature in case a certain sensor malfunction occurs using the proposed Adaptive Prognostic Malfunction Unit (APMU). This proposed coarse-grained Autonomous Landing Guidance Assistance System (ALGAS4) processing architecture has been optimized using different optimization techniques. The ALGAS4 architecture has been designed completely using VHDL, and the targeted FPGA was the INTEL Cyclone V 5CGXFC9D6F27C7 chip. According to the synthesis findings of the INTEL Quartus Prime software, the maximum working frequency of the ALGAS4 system is 278.24 MHz. In addition, the proposed ALGAS4 system could maintain a maximum computing performance of approximately 74.85 GOPS while using just 166.56 mW for dynamic and I/O power dissipation. △ Less

Submitted 13 January, 2024; originally announced January 2024.

Comments: Published in: IEEE Access ( Volume: 12) - Page(s): 2113 - 2122

AdaFlood: Adaptive Flood Regularization

Authors: Wonho Bae, Yi Ren, Mohamad Osama Ahmed, Frederick Tung, Danica J. Sutherland, Gabriel L. Oliveira

Abstract: Although neural networks are conventionally optimized towards zero training loss, it has been recently learned that targeting a non-zero training loss threshold, referred to as a flood level, often enables better test time generalization. Current approaches, however, apply the same constant flood level to all training samples, which inherently assumes all the samples have the same difficulty. We p… ▽ More Although neural networks are conventionally optimized towards zero training loss, it has been recently learned that targeting a non-zero training loss threshold, referred to as a flood level, often enables better test time generalization. Current approaches, however, apply the same constant flood level to all training samples, which inherently assumes all the samples have the same difficulty. We present AdaFlood, a novel flood regularization method that adapts the flood level of each training sample according to the difficulty of the sample. Intuitively, since training samples are not equal in difficulty, the target training loss should be conditioned on the instance. Experiments on datasets covering four diverse input modalities - text, images, asynchronous event sequences, and tabular - demonstrate the versatility of AdaFlood across data domains and noise levels. △ Less

Submitted 6 November, 2023; originally announced November 2023.

Tree Cross Attention

Authors: Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed

Abstract: Cross Attention is a popular method for retrieving information from a set of context tokens for making predictions. At inference time, for each prediction, Cross Attention scans the full set of $\mathcal{O}(N)$ tokens. In practice, however, often only a small subset of tokens are required for good performance. Methods such as Perceiver IO are cheap at inference as they distill the information to a… ▽ More Cross Attention is a popular method for retrieving information from a set of context tokens for making predictions. At inference time, for each prediction, Cross Attention scans the full set of $\mathcal{O}(N)$ tokens. In practice, however, often only a small subset of tokens are required for good performance. Methods such as Perceiver IO are cheap at inference as they distill the information to a smaller-sized set of latent tokens $L < N$ on which cross attention is then applied, resulting in only $\mathcal{O}(L)$ complexity. However, in practice, as the number of input tokens and the amount of information to distill increases, the number of latent tokens needed also increases significantly. In this work, we propose Tree Cross Attention (TCA) - a module based on Cross Attention that only retrieves information from a logarithmic $\mathcal{O}(\log(N))$ number of tokens for performing inference. TCA organizes the data in a tree structure and performs a tree search at inference time to retrieve the relevant tokens for prediction. Leveraging TCA, we introduce ReTreever, a flexible architecture for token-efficient inference. We show empirically that Tree Cross Attention (TCA) performs comparable to Cross Attention across various classification and uncertainty regression tasks while being significantly more token-efficient. Furthermore, we compare ReTreever against Perceiver IO, showing significant gains while using the same number of tokens for inference. △ Less

Submitted 1 March, 2024; v1 submitted 29 September, 2023; originally announced September 2023.

Comments: Accepted by ICLR 2024

MVD:A Novel Methodology and Dataset for Acoustic Vehicle Type Classification

Authors: Mohd Ashhad, Omar Ahmed, Sooraj K. Ambat, Zeeshan Ali Haq, Mansaf Alam

Abstract: Rising urban populations have led to a surge in vehicle use and made traffic monitoring and management indispensable. Acoustic traffic monitoring (ATM) offers a cost-effective and efficient alternative to more computationally expensive methods of monitoring traffic such as those involving computer vision technologies. In this paper, we present MVD and MVDA: two open datasets for the development of… ▽ More Rising urban populations have led to a surge in vehicle use and made traffic monitoring and management indispensable. Acoustic traffic monitoring (ATM) offers a cost-effective and efficient alternative to more computationally expensive methods of monitoring traffic such as those involving computer vision technologies. In this paper, we present MVD and MVDA: two open datasets for the development of acoustic traffic monitoring and vehicle-type classification algorithms, which contain audio recordings of moving vehicles. The dataset contain four classes- Trucks, Cars, Motorbikes, and a No-vehicle class. Additionally, we propose a novel and efficient way to accurately classify these acoustic signals using cepstrum and spectrum based local and global audio features, and a multi-input neural network. Experimental results show that our methodology improves upon the established baselines of previous works and achieves an accuracy of 91.98% and 96.66% on MVD and MVDA Datasets, respectively. Finally, the proposed model was deployed through an Android application to make it accessible for testing and demonstrate its efficacy. △ Less

Submitted 7 September, 2023; originally announced September 2023.

ANER: Arabic and Arabizi Named Entity Recognition using Transformer-Based Approach

Authors: Abdelrahman "Boda" Sadallah, Omar Ahmed, Shimaa Mohamed, Omar Hatem, Doaa Hesham, Ahmed H. Yousef

Abstract: One of the main tasks of Natural Language Processing (NLP), is Named Entity Recognition (NER). It is used in many applications and also can be used as an intermediate step for other tasks. We present ANER, a web-based named entity recognizer for the Arabic, and Arabizi languages. The model is built upon BERT, which is a transformer-based encoder. It can recognize 50 different entity classes, cover… ▽ More One of the main tasks of Natural Language Processing (NLP), is Named Entity Recognition (NER). It is used in many applications and also can be used as an intermediate step for other tasks. We present ANER, a web-based named entity recognizer for the Arabic, and Arabizi languages. The model is built upon BERT, which is a transformer-based encoder. It can recognize 50 different entity classes, covering various fields. We trained our model on the WikiFANE\_Gold dataset which consists of Wikipedia articles. We achieved an F1 score of 88.7\%, which beats CAMeL Tools' F1 score of 83\% on the ANERcorp dataset, which has only 4 classes. We also got an F1 score of 77.7\% on the NewsFANE\_Gold dataset which contains out-of-domain data from News articles. The system is deployed on a user-friendly web interface that accepts users' inputs in Arabic, or Arabizi. It allows users to explore the entities in the text by highlighting them. It can also direct users to get information about entities through Wikipedia directly. We added the ability to do NER using our model, or CAMeL Tools' model through our website. ANER is publicly accessible at \url{http://www.aner.online}. We also deployed our model on HuggingFace at https://huggingface.co/boda/ANER, to allow developers to test and use it. △ Less

Submitted 28 August, 2023; originally announced August 2023.

Constant Memory Attention Block

Authors: Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed

Abstract: Modern foundation model architectures rely on attention mechanisms to effectively capture context. However, these methods require linear or quadratic memory in terms of the number of inputs/datapoints, limiting their applicability in low-compute domains. In this work, we propose Constant Memory Attention Block (CMAB), a novel general-purpose attention block that computes its output in constant mem… ▽ More Modern foundation model architectures rely on attention mechanisms to effectively capture context. However, these methods require linear or quadratic memory in terms of the number of inputs/datapoints, limiting their applicability in low-compute domains. In this work, we propose Constant Memory Attention Block (CMAB), a novel general-purpose attention block that computes its output in constant memory and performs updates in constant computation. Highlighting CMABs efficacy, we introduce methods for Neural Processes and Temporal Point Processes. Empirically, we show our proposed methods achieve results competitive with state-of-the-art while being significantly more memory efficient. △ Less

Submitted 21 June, 2023; originally announced June 2023.

Comments: Workshop version of arXiv:2305.14567

Segregated FLS Processing Cores for V/STOL Autonomous Landing Guidance Assistant System using FPGA

Authors: Hossam O. Ahmed

Abstract: It is highly predicted that the roads and parking areas will be extremely congested with vehicles to the point that searching for a novel solution will not be an optional choice for conserving the sustainability rate of the overall humanity's development growth. Such issue could be overcome by developing modified generations of the Urban Air Mobility (UAM) vehicles that essentially depend on the V… ▽ More It is highly predicted that the roads and parking areas will be extremely congested with vehicles to the point that searching for a novel solution will not be an optional choice for conserving the sustainability rate of the overall humanity's development growth. Such issue could be overcome by developing modified generations of the Urban Air Mobility (UAM) vehicles that essentially depend on the Vertical and/or Short Take-Off and Landing (V/STOL) feature to increase the efficiency of landing capabilities on limited-space parking areas. The complexity of integrating an efficient and safe V/STOL feature in such UAM vehicles is notably difficult comparing with the conventional and normal techniques for landing and take-off. The efficient V/STOL feature should be carried out by a complete and collaborative Cyber-Physical System (CPS) processing architecture, such as the CPS-5C architecture. In this paper, we only proposed two CPS-5C physical layers of a V/STOL Autonomous Landing Guidance Assistant System (ALGAS2) processing unit to increase the reliability of the vertical landing mechanism. The proposed V/STOL-ALGAS2 system depends on Fuzzy Logic System (FLS) as the advanced control unit. Furthermore, the proposed ALGAS2 system depends on four symmetric and segregated processing ALGAS2 cores that processing the data in a fully parallel and independent manner to enhance many essential security and safety factors for the futuristic UAM vehicles. The proposed ALGAS2 digital circuits architecture has been designed using MATLAB and VHDL. Also, it has been further analyzed for the implementation and validation tests using the Intel Altera OpenVINO FPGA board. The proposed ALGAS processing unit attained a maximum computational processing performance of about 21.22 Giga Operations per Seconds (GOPS). △ Less

Submitted 5 June, 2023; originally announced June 2023.

Comments: 2021 Integrated Communications Navigation and Surveillance Conference (ICNS), Dulles, VA, USA

Memory Efficient Neural Processes via Constant Memory Attention Block

Authors: Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed

Abstract: Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty. Recent state-of-the-art methods, however, leverage expensive attention mechanisms, limiting their applications, particularly in low-resource settings. In this work, we propose Constant Memory Attentive Neural Processes (CMANPs), an NP variant that only requires constant memory. To do so, we f… ▽ More Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty. Recent state-of-the-art methods, however, leverage expensive attention mechanisms, limiting their applications, particularly in low-resource settings. In this work, we propose Constant Memory Attentive Neural Processes (CMANPs), an NP variant that only requires constant memory. To do so, we first propose an efficient update operation for Cross Attention. Leveraging the update operation, we propose Constant Memory Attention Block (CMAB), a novel attention block that (i) is permutation invariant, (ii) computes its output in constant memory, and (iii) performs constant computation updates. Finally, building on CMAB, we detail Constant Memory Attentive Neural Processes. Empirically, we show CMANPs achieve state-of-the-art results on popular NP benchmarks while being significantly more memory efficient than prior methods. △ Less

Submitted 27 May, 2024; v1 submitted 23 May, 2023; originally announced May 2023.

Fault Tolerant Processing Unit Using Gamma Distribution Sliding Window For Autonomous Landing Guidance System

Authors: Hossam O. Ahmed

Abstract: To keep up with today's dense metropolitan areas and their accompanying traffic problems, a growing number of towns are looking for more advanced and swift urban taxi drones. The safety parameters that must be taken into consideration may be the most important element in the widespread use of such technology. Most recent aviation mishaps have happened during the landing phase, making this a partic… ▽ More To keep up with today's dense metropolitan areas and their accompanying traffic problems, a growing number of towns are looking for more advanced and swift urban taxi drones. The safety parameters that must be taken into consideration may be the most important element in the widespread use of such technology. Most recent aviation mishaps have happened during the landing phase, making this a particularly important safety consideration for Vertical and/or Short Take-Off and Landing (V/STOL) drones. In this study, we focused on improving the fault tolerance of the processor architectures used by the predecessors of Autonomous Landing Guidance Assistance Systems (ALGAS), which in turn improves their decision-making capabilities. Furthermore, this is achieved by proposing a fault-tolerant processing architecture that depends on the Gamma Distribution Sliding Window Unit (GDSWU). This proposed GDSWU has been designed completely using VHDL, and the targeted FPFA was the Intel Cyclone V 5CGXFC9D6F27C7 chip. The GDSWU could operate at a maximum frequency of 369.96 MHz, as calculated by the synthesis results of the INTEL Quartus Prime program. The suggested GDSWU core only requires 20.36 mW for dynamic core and I/O power consumption. △ Less

Submitted 3 June, 2023; v1 submitted 2 May, 2023; originally announced May 2023.

Comments: 21st IEEE Interregional NEWCAS Conference, Edinburgh, Scotland

Coarse Grained FLS-based Processor with Prognostic Malfunction Feature for UAM Drones using FPGA

Authors: Hossam O. Ahmed

Abstract: Many overall safety factors need to be considered in the next generation of Urban Air Mobility (UAM) systems and addressing these can become the anchor point for such technology to reach consent for worldwide application. On the other hand, fulfilling the safety requirements from an exponential increase of prolific UAM systems, is extremely complicated, and requires careful consideration of a vari… ▽ More Many overall safety factors need to be considered in the next generation of Urban Air Mobility (UAM) systems and addressing these can become the anchor point for such technology to reach consent for worldwide application. On the other hand, fulfilling the safety requirements from an exponential increase of prolific UAM systems, is extremely complicated, and requires careful consideration of a variety of issues. One of the key goals of these Unmanned Air Systems (UAS) is the requirement to support the launch and control of hundreds of thousands of these advanced drones in the air simultaneously. Given the impracticalities of training the corresponding number of expert pilots, achieving this goal can only be realized through safe operation in either fullautonomous or semi-autonomous modes. According to many recent studies, the majority of flight accidents are concentrated on the last three stages of a flight trip, which include the Initial Approach, Final Approach, and Landing Phases of an airplane trip. Therefore, this paper proposes a novel decentralized processing system for enhancing the safety factors during the critical phases of Vertical and/or Short Take-Off and Landing (V/STOL) drones. This has been achieved by adopting several processing and control algorithms such as an Open Fuzzy Logic System (FLS) integrated with a Flight Rules Unit (FRU), FIR filters, and a novel Prognostic Malfunction processing unit. After applying several optimization techniques, this novel coarse-grained Autonomous Landing Guidance Assistance System (ALGAS3) processing architecture has been optimized to achieve a maximum computational processing performance of 70.82 Giga Operations per Second (GOPS). Also, the proposed ALGAS3 system shows an ultra-low dynamic thermal power dissipation (I/O and core) of 145.4 mW which is ideal for mobile avionic systems using INTEL 5CGXFC9D6F27C7 FPGA chip. △ Less

Submitted 4 April, 2023; originally announced April 2023.

Comments: The paper is accepted

Journal ref: The 23rd Integrated Communications, Navigation, and Surveillance Conference, 2023, USA

Meta Temporal Point Processes

Authors: Wonho Bae, Mohamed Osama Ahmed, Frederick Tung, Gabriel L. Oliveira

Abstract: A temporal point process (TPP) is a stochastic process where its realization is a sequence of discrete events in time. Recent work in TPPs model the process using a neural network in a supervised learning framework, where a training set is a collection of all the sequences. In this work, we propose to train TPPs in a meta learning framework, where each sequence is treated as a different task, via… ▽ More A temporal point process (TPP) is a stochastic process where its realization is a sequence of discrete events in time. Recent work in TPPs model the process using a neural network in a supervised learning framework, where a training set is a collection of all the sequences. In this work, we propose to train TPPs in a meta learning framework, where each sequence is treated as a different task, via a novel framing of TPPs as neural processes (NPs). We introduce context sets to model TPPs as an instantiation of NPs. Motivated by attentive NP, we also introduce local history matching to help learn more informative features. We demonstrate the potential of the proposed method on popular public benchmark datasets and tasks, and compare with state-of-the-art TPP methods. △ Less

Submitted 27 January, 2023; originally announced January 2023.

Comments: Accepted to ICLR2023

Gumbel-Softmax Selective Networks

Authors: Mahmoud Salem, Mohamed Osama Ahmed, Frederick Tung, Gabriel Oliveira

Abstract: ML models often operate within the context of a larger system that can adapt its response when the ML model is uncertain, such as falling back on safe defaults or a human in the loop. This commonly encountered operational context calls for principled techniques for training ML models with the option to abstain from predicting when uncertain. Selective neural networks are trained with an integrated… ▽ More ML models often operate within the context of a larger system that can adapt its response when the ML model is uncertain, such as falling back on safe defaults or a human in the loop. This commonly encountered operational context calls for principled techniques for training ML models with the option to abstain from predicting when uncertain. Selective neural networks are trained with an integrated option to abstain, allowing them to learn to recognize and optimize for the subset of the data distribution for which confident predictions can be made. However, optimizing selective networks is challenging due to the non-differentiability of the binary selection function (the discrete decision of whether to predict or abstain). This paper presents a general method for training selective networks that leverages the Gumbel-softmax reparameterization trick to enable selection within an end-to-end differentiable training framework. Experiments on public datasets demonstrate the potential of Gumbel-softmax selective networks for selective regression and classification. △ Less

Submitted 18 November, 2022; originally announced November 2022.

Latent Bottlenecked Attentive Neural Processes

Authors: Leo Feng, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed

Abstract: Neural Processes (NPs) are popular methods in meta-learning that can estimate predictive uncertainty on target datapoints by conditioning on a context dataset. Previous state-of-the-art method Transformer Neural Processes (TNPs) achieve strong performance but require quadratic computation with respect to the number of context datapoints, significantly limiting its scalability. Conversely, existing… ▽ More Neural Processes (NPs) are popular methods in meta-learning that can estimate predictive uncertainty on target datapoints by conditioning on a context dataset. Previous state-of-the-art method Transformer Neural Processes (TNPs) achieve strong performance but require quadratic computation with respect to the number of context datapoints, significantly limiting its scalability. Conversely, existing sub-quadratic NP variants perform significantly worse than that of TNPs. Tackling this issue, we propose Latent Bottlenecked Attentive Neural Processes (LBANPs), a new computationally efficient sub-quadratic NP variant, that has a querying computational complexity independent of the number of context datapoints. The model encodes the context dataset into a constant number of latent vectors on which self-attention is performed. When making predictions, the model retrieves higher-order information from the context dataset via multiple cross-attention mechanisms on the latent vectors. We empirically show that LBANPs achieve results competitive with the state-of-the-art on meta-regression, image completion, and contextual multi-armed bandits. We demonstrate that LBANPs can trade-off the computational cost and performance according to the number of latent vectors. Finally, we show LBANPs can scale beyond existing attention-based NP variants to larger dataset settings. △ Less

Submitted 1 March, 2023; v1 submitted 15 November, 2022; originally announced November 2022.

Towards Better Selective Classification

Authors: Leo Feng, Mohamed Osama Ahmed, Hossein Hajimirsadeghi, Amir Abdi

Abstract: We tackle the problem of Selective Classification where the objective is to achieve the best performance on a predetermined ratio (coverage) of the dataset. Recent state-of-the-art selective methods come with architectural changes either via introducing a separate selection head or an extra abstention logit. In this paper, we challenge the aforementioned methods. The results suggest that the super… ▽ More We tackle the problem of Selective Classification where the objective is to achieve the best performance on a predetermined ratio (coverage) of the dataset. Recent state-of-the-art selective methods come with architectural changes either via introducing a separate selection head or an extra abstention logit. In this paper, we challenge the aforementioned methods. The results suggest that the superior performance of state-of-the-art methods is owed to training a more generalizable classifier rather than their proposed selection mechanisms. We argue that the best performing selection mechanism should instead be rooted in the classifier itself. Our proposed selection strategy uses the classification scores and achieves better results by a significant margin, consistently, across all coverages and all datasets, without any added compute cost. Furthermore, inspired by semi-supervised learning, we propose an entropy-based regularizer that improves the performance of selective classification methods. Our proposed selection mechanism with the proposed entropy-based regularizer achieves new state-of-the-art results. △ Less

Submitted 1 March, 2023; v1 submitted 17 June, 2022; originally announced June 2022.

Monotonicity Regularization: Improved Penalties and Novel Applications to Disentangled Representation Learning and Robust Classification

Authors: Joao Monteiro, Mohamed Osama Ahmed, Hossein Hajimirsadeghi, Greg Mori

Abstract: We study settings where gradient penalties are used alongside risk minimization with the goal of obtaining predictors satisfying different notions of monotonicity. Specifically, we present two sets of contributions. In the first part of the paper, we show that different choices of penalties define the regions of the input space where the property is observed. As such, previous methods result in mo… ▽ More We study settings where gradient penalties are used alongside risk minimization with the goal of obtaining predictors satisfying different notions of monotonicity. Specifically, we present two sets of contributions. In the first part of the paper, we show that different choices of penalties define the regions of the input space where the property is observed. As such, previous methods result in models that are monotonic only in a small volume of the input space. We thus propose an approach that uses mixtures of training instances and random points to populate the space and enforce the penalty in a much larger region. As a second set of contributions, we introduce regularization strategies that enforce other notions of monotonicity in different settings. In this case, we consider applications, such as image classification and generative modeling, where monotonicity is not a hard constraint but can help improve some aspects of the model. Namely, we show that inducing monotonicity can be beneficial in applications such as: (1) allowing for controllable data generation, (2) defining strategies to detect anomalous data, and (3) generating explanations for predictions. Our proposed approaches do not introduce relevant computational overhead while leading to efficient procedures that provide extra benefits over baseline models. △ Less

Submitted 17 May, 2022; originally announced May 2022.

Comments: Accepted to UAI 2022

AI-Bind: Improving Binding Predictions for Novel Protein Targets and Ligands

Authors: Ayan Chatterjee, Robin Walters, Zohair Shafi, Omair Shafi Ahmed, Michael Sebek, Deisy Gysi, Rose Yu, Tina Eliassi-Rad, Albert-László Barabási, Giulia Menichetti

Abstract: Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We first unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortc… ▽ More Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We first unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Then, we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training, allowing us to limit the annotation imbalance and improve binding predictions for novel proteins and ligands. We illustrate the value of AI-Bind by predicting drugs and natural compounds with binding affinity to SARS-CoV-2 viral proteins and the associated human proteins. We also validate these predictions via docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. Overall, AI-Bind offers a powerful high-throughput approach to identify drug-target combinations, with the potential of becoming a powerful tool in drug discovery. △ Less

Submitted 9 November, 2022; v1 submitted 24 December, 2021; originally announced December 2021.

Comments: 83 pages, 26 figures, all references moved to a single section, new results added on AI interpretability, added comparison with MolTrans, added validation using gold standard experimental data

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

Authors: Ossama Ahmed, Frederik Träuble, Anirudh Goyal, Alexander Neitz, Yoshua Bengio, Bernhard Schölkopf, Manuel Wüthrich, Stefan Bauer

Abstract: Despite recent successes of reinforcement learning (RL), it remains a challenge for agents to transfer learned skills to related environments. To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment. The environment is a simulation of an open-source robotic platform, hence offering the poss… ▽ More Despite recent successes of reinforcement learning (RL), it remains a challenge for agents to transfer learned skills to related environments. To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment. The environment is a simulation of an open-source robotic platform, hence offering the possibility of sim-to-real transfer. Tasks consist of constructing 3D shapes from a given set of blocks - inspired by how children learn to build complex structures. The key strength of CausalWorld is that it provides a combinatorial family of such tasks with common causal structure and underlying factors (including, e.g., robot and object masses, colors, sizes). The user (or the agent) may intervene on all causal variables, which allows for fine-grained control over how similar different tasks (or task distributions) are. One can thus easily define training and evaluation distributions of a desired difficulty level, targeting a specific form of generalization (e.g., only changes in appearance or object mass). Further, this common parametrization facilitates defining curricula by interpolating between an initial and a target task. While users may define their own task distributions, we present eight meaningful distributions as concrete benchmarks, ranging from simple to very challenging, all of which require long-horizon planning as well as precise low-level motor control. Finally, we provide baseline results for a subset of these tasks on distinct training curricula and corresponding evaluation protocols, verifying the feasibility of the tasks in this benchmark. △ Less

Submitted 24 November, 2020; v1 submitted 8 October, 2020; originally announced October 2020.

Comments: The first two authors contributed equally, the last two authors avised jointly

Point Process Flows

Authors: Nazanin Mehrasa, Ruizhi Deng, Mohamed Osama Ahmed, Bo Chang, Jiawei He, Thibaut Durand, Marcus Brubaker, Greg Mori

Abstract: Event sequences can be modeled by temporal point processes (TPPs) to capture their asynchronous and probabilistic nature. We propose an intensity-free framework that directly models the point process distribution by utilizing normalizing flows. This approach is capable of capturing highly complex temporal distributions and does not rely on restrictive parametric forms. Comparisons with state-of-th… ▽ More Event sequences can be modeled by temporal point processes (TPPs) to capture their asynchronous and probabilistic nature. We propose an intensity-free framework that directly models the point process distribution by utilizing normalizing flows. This approach is capable of capturing highly complex temporal distributions and does not rely on restrictive parametric forms. Comparisons with state-of-the-art baseline models on both synthetic and challenging real-life datasets show that the proposed framework is effective at modeling the stochasticity of discrete event sequences. △ Less

Submitted 22 December, 2019; v1 submitted 18 October, 2019; originally announced October 2019.

Human Intracranial EEG Quantitative Analysis and Automatic Feature Learning for Epileptic Seizure Prediction

Authors: Ramy Hussein, Mohamed Osama Ahmed, Rabab Ward, Z. Jane Wang, Levin Kuhlmann, Yi Guo

Abstract: Objective: The aim of this study is to develop an efficient and reliable epileptic seizure prediction system using intracranial EEG (iEEG) data, especially for people with drug-resistant epilepsy. The prediction procedure should yield accurate results in a fast enough fashion to alert patients of impending seizures. Methods: We quantitatively analyze the human iEEG data to obtain insights into how… ▽ More Objective: The aim of this study is to develop an efficient and reliable epileptic seizure prediction system using intracranial EEG (iEEG) data, especially for people with drug-resistant epilepsy. The prediction procedure should yield accurate results in a fast enough fashion to alert patients of impending seizures. Methods: We quantitatively analyze the human iEEG data to obtain insights into how the human brain behaves before and between epileptic seizures. We then introduce an efficient pre-processing method for reducing the data size and converting the time-series iEEG data into an image-like format that can be used as inputs to convolutional neural networks (CNNs). Further, we propose a seizure prediction algorithm that uses cooperative multi-scale CNNs for automatic feature learning of iEEG data. Results: 1) iEEG channels contain complementary information and excluding individual channels is not advisable to retain the spatial information needed for accurate prediction of epileptic seizures. 2) The traditional PCA is not a reliable method for iEEG data reduction in seizure prediction. 3) Hand-crafted iEEG features may not be suitable for reliable seizure prediction performance as the iEEG data varies between patients and over time for the same patient. 4) Seizure prediction results show that our algorithm outperforms existing methods by achieving an average sensitivity of 87.85% and AUC score of 0.84. Conclusion: Understanding how the human brain behaves before seizure attacks and far from them facilitates better designs of epileptic seizure predictors. Significance: Accurate seizure prediction algorithms can warn patients about the next seizure attack so they could avoid dangerous activities. Medications could then be administered to abort the impending seizure and minimize the risk of injury. △ Less

Submitted 7 April, 2019; originally announced April 2019.

Combining Bayesian Optimization and Lipschitz Optimization

Authors: Mohamed Osama Ahmed, Sharan Vaswani, Mark Schmidt

Abstract: Bayesian optimization and Lipschitz optimization have developed alternative techniques for optimizing black-box functions. They each exploit a different form of prior about the function. In this work, we explore strategies to combine these techniques for better global optimization. In particular, we propose ways to use the Lipschitz continuity assumption within traditional BO algorithms, which we… ▽ More Bayesian optimization and Lipschitz optimization have developed alternative techniques for optimizing black-box functions. They each exploit a different form of prior about the function. In this work, we explore strategies to combine these techniques for better global optimization. In particular, we propose ways to use the Lipschitz continuity assumption within traditional BO algorithms, which we call Lipschitz Bayesian optimization (LBO). This approach does not increase the asymptotic runtime and in some cases drastically improves the performance (while in the worst-case the performance is similar). Indeed, in a particular setting, we prove that using the Lipschitz information yields the same or a better bound on the regret compared to using Bayesian optimization on its own. Moreover, we propose a simple heuristics to estimate the Lipschitz constant, and prove that a growing estimate of the Lipschitz constant is in some sense ``harmless''. Our experiments on 15 datasets with 4 acquisition functions show that in the worst case LBO performs similar to the underlying BO method while in some cases it performs substantially better. Thompson sampling in particular typically saw drastic improvements (as the Lipschitz information corrected for its well-known ``over-exploration'' phenomenon) and its LBO variant often outperformed other acquisition functions. △ Less

Submitted 28 July, 2020; v1 submitted 9 October, 2018; originally announced October 2018.

Stop Wasting My Gradients: Practical SVRG

Authors: Reza Babanezhad, Mohamed Osama Ahmed, Alim Virani, Mark Schmidt, Jakub Konečný, Scott Sallinen

Abstract: We present and analyze several strategies for improving the performance of stochastic variance-reduced gradient (SVRG) methods. We first show that the convergence rate of these methods can be preserved under a decreasing sequence of errors in the control variate, and use this to derive variants of SVRG that use growing-batch strategies to reduce the number of gradient calculations required in the… ▽ More We present and analyze several strategies for improving the performance of stochastic variance-reduced gradient (SVRG) methods. We first show that the convergence rate of these methods can be preserved under a decreasing sequence of errors in the control variate, and use this to derive variants of SVRG that use growing-batch strategies to reduce the number of gradient calculations required in the early iterations. We further (i) show how to exploit support vectors to reduce the number of gradient computations in the later iterations, (ii) prove that the commonly-used regularized SVRG iteration is justified and improves the convergence rate, (iii) consider alternate mini-batch selection strategies, and (iv) consider the generalization error of the method. △ Less

Submitted 5 November, 2015; originally announced November 2015.

Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields

Authors: Mark Schmidt, Reza Babanezhad, Mohamed Osama Ahmed, Aaron Defazio, Ann Clifton, Anoop Sarkar

Abstract: We apply stochastic average gradient (SAG) algorithms for training conditional random fields (CRFs). We describe a practical implementation that uses structure in the CRF gradient to reduce the memory requirement of this linearly-convergent stochastic gradient method, propose a non-uniform sampling scheme that substantially improves practical performance, and analyze the rate of convergence of the… ▽ More We apply stochastic average gradient (SAG) algorithms for training conditional random fields (CRFs). We describe a practical implementation that uses structure in the CRF gradient to reduce the memory requirement of this linearly-convergent stochastic gradient method, propose a non-uniform sampling scheme that substantially improves practical performance, and analyze the rate of convergence of the SAGA variant under non-uniform sampling. Our experimental results reveal that our method often significantly outperforms existing methods in terms of the training objective, and performs as well or better than optimally-tuned stochastic gradient methods in terms of test error. △ Less

Submitted 16 April, 2015; originally announced April 2015.

Comments: AI/Stats 2015, 24 pages

Decentralized, Adaptive, Look-Ahead Particle Filtering

Authors: Mohamed Osama Ahmed, Pouyan T. Bibalan, Nando de Freitas, Simon Fauvel

Abstract: The decentralized particle filter (DPF) was proposed recently to increase the level of parallelism of particle filtering. Given a decomposition of the state space into two nested sets of variables, the DPF uses a particle filter to sample the first set and then conditions on this sample to generate a set of samples for the second set of variables. The DPF can be understood as a variant of the popu… ▽ More The decentralized particle filter (DPF) was proposed recently to increase the level of parallelism of particle filtering. Given a decomposition of the state space into two nested sets of variables, the DPF uses a particle filter to sample the first set and then conditions on this sample to generate a set of samples for the second set of variables. The DPF can be understood as a variant of the popular Rao-Blackwellized particle filter (RBPF), where the second step is carried out using Monte Carlo approximations instead of analytical inference. As a result, the range of applications of the DPF is broader than the one for the RBPF. In this paper, we improve the DPF in two ways. First, we derive a Monte Carlo approximation of the optimal proposal distribution and, consequently, design and implement a more efficient look-ahead DPF. Although the decentralized filters were initially designed to capitalize on parallel implementation, we show that the look-ahead DPF can outperform the standard particle filter even on a single machine. Second, we propose the use of bandit algorithms to automatically configure the state space decomposition of the DPF. △ Less

Submitted 11 March, 2012; originally announced March 2012.

Comments: 16 pages, 11 figures, Authorship in alphabetical order