Showing 1–24 of 24 results for author: Chaudhuri, R

Effective pruning of task-trained recurrent neural networks using noisy fluctuations and connection rescaling

Authors: Sanjith Senthil, Rishidev Chaudhuri

Abstract: The pruning of network connections is key to brain function but, despite its importance, there exist few biologically-plausible pruning rules with demonstrated good performance. In this work we evaluate noise-prune, a recently introduced unsupervised local pruning rule for recurrent networks that uses noisy fluctuations to determine the importance of connections. Noise-prune has previously only be… ▽ More The pruning of network connections is key to brain function but, despite its importance, there exist few biologically-plausible pruning rules with demonstrated good performance. In this work we evaluate noise-prune, a recently introduced unsupervised local pruning rule for recurrent networks that uses noisy fluctuations to determine the importance of connections. Noise-prune has previously only been empirically tested on random networks without a specific computational function. We show that noise-prune preserves task-performance in task-trained recurrent neural networks, greatly outperforming a strategy that only uses the magnitude of connections and performing on par with or exceeding a non-local strategy that uses second-order information. Rather than deterministically removing connections that fall below a certain threshold importance, noise-prune samples connections to preserve based on their importance and strengthens retained connections to preserve average synaptic strength. We show that this sampling and rescaling is essential to good performance, but that the optimal empirical degree of rescaling is lower than that predicted by the original theoretical argument. Our work thus validates noise-prune as a biologically-plausible pruning rule for functional recurrent network architectures and characterizes its optimal parameter settings. △ Less

Submitted 5 August, 2026; originally announced August 2026.

OpenAI GPT-5 System Card

Authors: Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, Akshay Nathan, Alan Luo, Alec Helyar, Aleksander Madry, Aleksandr Efremov, Aleksandra Spyra, Alex Baker-Whitcomb, Alex Beutel, Alex Karpenko, Alex Makelov, Alex Neitz, Alex Wei, Alexandra Barr, Alexandre Kirchmeyer, Alexey Ivanov , et al. (461 additional authors not shown)

Abstract: This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in… ▽ More This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach. △ Less

Submitted 1 May, 2026; v1 submitted 19 December, 2025; originally announced January 2026.

Comments: May 2026: Added monitorability evals and authors

Enhancing Road Safety Through Multi-Camera Image Segmentation with Post-Encroachment Time Analysis

Authors: Shounak Ray Chaudhuri, Arash Jahangiri, Christopher Paolini

Abstract: Traffic safety analysis at signalized intersections is vital for reducing vehicle and pedestrian collisions, yet traditional crash-based studies are limited by data sparsity and latency. This paper presents a novel multi-camera computer vision framework for real-time safety assessment through Post-Encroachment Time (PET) computation, demonstrated at the intersection of H Street and Broadway in Chu… ▽ More Traffic safety analysis at signalized intersections is vital for reducing vehicle and pedestrian collisions, yet traditional crash-based studies are limited by data sparsity and latency. This paper presents a novel multi-camera computer vision framework for real-time safety assessment through Post-Encroachment Time (PET) computation, demonstrated at the intersection of H Street and Broadway in Chula Vista, California. Four synchronized cameras provide continuous visual coverage, with each frame processed on NVIDIA Jetson AGX Xavier devices using YOLOv11 segmentation for vehicle detection. Detected vehicle polygons are transformed into a unified bird's-eye map using homography matrices, enabling alignment across overlapping camera views. A novel pixel-level PET algorithm measures vehicle position without reliance on fixed cells, allowing fine-grained hazard visualization via dynamic heatmaps, accurate to 3.3 sq-cm. Timestamped vehicle and PET data is stored in an SQL database for long-term monitoring. Results over various time intervals demonstrate the framework's ability to identify high-risk regions with sub-second precision and real-time throughput on edge devices, producing data for an 800 x 800 pixel logarithmic heatmap at an average of 2.68 FPS. This study validates the feasibility of decentralized vision-based PET analysis for intelligent transportation systems, offering a replicable methodology for high-resolution, real-time, and scalable intersection safety evaluation. △ Less

Submitted 14 November, 2025; originally announced November 2025.

Comments: 8 pages, 10 figures, Submitted to IEEE Intelligent Vehicles Symposium 2026

Exploring listeners' perceptions of AI-generated and human-composed music for functional emotional applications

Authors: Kimaya Lecamwasam, Tishya Ray Chaudhuri

Abstract: This work investigates how listeners perceive and evaluate AI-generated as compared to human-composed music in the context of emotional resonance and regulation. Across a mixed-methods design, participants were exposed to both AI and human music under various labeling conditions (music correctly labeled as AI- or human-origin, music incorrectly labeled as AI- or human-origin, and unlabeled music)… ▽ More This work investigates how listeners perceive and evaluate AI-generated as compared to human-composed music in the context of emotional resonance and regulation. Across a mixed-methods design, participants were exposed to both AI and human music under various labeling conditions (music correctly labeled as AI- or human-origin, music incorrectly labeled as AI- or human-origin, and unlabeled music) and emotion cases (Calm and Upbeat), and were asked to rate preference, efficacy of target emotion elicitation, and emotional impact. Participants were significantly more likely to rate human-composed music, regardless of labeling, as more effective at eliciting target emotional states, though quantitative analyses revealed no significant differences in emotional response. However, participants were significantly more likely to indicate preference for AI-generated music, yielding further questions regarding the impact of emotional authenticity and perceived authorship on musical appraisal. Qualitative data underscored this, with participants associating humanness with qualities such as imperfection, flow, and 'soul.' These findings challenge the assumption that preference alone signals success in generative music systems. Rather than positioning AI tools as replacements for human creativity or emotional expression, they point toward a more careful design ethos that acknowledges the limits of replication and prioritizes human values such as authenticity, individuality, and emotion regulation in wellness and affective technologies. △ Less

Submitted 3 June, 2025; originally announced June 2025.

Comments: 18 pages (includes references and appendix), 2 figures, 5 tables (includes 1 in appendix), and appendix

A Framework for Testing and Adapting REST APIs as LLM Tools

Authors: Jayachandu Bandlamudi, Ritwik Chaudhuri, Neelamadhav Gantayat, Sambit Ghosh, Kushal Mukherjee, Prerna Agarwal, Renuka Sindhgatta, Sameep Mehta

Abstract: Large Language Models (LLMs) are increasingly used to build autonomous agents that perform complex tasks with external tools, often exposed through APIs in enterprise systems. Direct use of these APIs is difficult due to the complex input schema and verbose responses. Current benchmarks overlook these challenges, leaving a gap in assessing API readiness for agent-driven automation. We present a te… ▽ More Large Language Models (LLMs) are increasingly used to build autonomous agents that perform complex tasks with external tools, often exposed through APIs in enterprise systems. Direct use of these APIs is difficult due to the complex input schema and verbose responses. Current benchmarks overlook these challenges, leaving a gap in assessing API readiness for agent-driven automation. We present a testing framework that systematically evaluates enterprise APIs when wrapped as Python tools for LLM-based agents. The framework generates data-aware test cases, translates them into natural language instructions, and evaluates whether agents can correctly invoke the tool, handle their inputs, and process its responses. We apply the framework to generate over 2400 test cases across different domains and develop a taxonomy of common errors, including input misinterpretation, output failures, and schema mismatches. We further classify errors to support debugging and tool refinement. Our framework provides a systematic approach to enabling enterprise APIs as reliable tools for agent-based applications. △ Less

Submitted 12 September, 2025; v1 submitted 21 April, 2025; originally announced April 2025.

ACM Class: I.2.7

OpenAI o1 System Card

Authors: OpenAI, :, Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, Alex Iftimie, Alex Karpenko, Alex Tachard Passos, Alexander Neitz, Alexander Prokofiev, Alexander Wei, Allison Tam, Ally Bennett, Ananya Kumar, Andre Saraiva, Andrea Vallone, Andrew Duberstein, Andrew Kondrich , et al. (240 additional authors not shown)

Abstract: The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In particular, our models can reason about our safety policies in context when responding to potentially unsafe prompts, through deliberative alignment. This leads to state-of-the-ar… ▽ More The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In particular, our models can reason about our safety policies in context when responding to potentially unsafe prompts, through deliberative alignment. This leads to state-of-the-art performance on certain benchmarks for risks such as generating illicit advice, choosing stereotyped responses, and succumbing to known jailbreaks. Training models to incorporate a chain of thought before answering has the potential to unlock substantial benefits, while also increasing potential risks that stem from heightened intelligence. Our results underscore the need for building robust alignment methods, extensively stress-testing their efficacy, and maintaining meticulous risk management protocols. This report outlines the safety work carried out for the OpenAI o1 and OpenAI o1-mini models, including safety evaluations, external red teaming, and Preparedness Framework evaluations. △ Less

Submitted 29 April, 2026; v1 submitted 21 December, 2024; originally announced December 2024.

Harnessing and modulating chaos to sample from neural generative models

Authors: Rishidev Chaudhuri, Vivek Handebagh

Abstract: Chaos is generic in strongly-coupled recurrent networks of model neurons, and thought to be an easily accessible dynamical regime in the brain. While neural chaos is typically seen as an impediment to robust computation, we show how such chaos might play a functional role in allowing the brain to learn and sample from generative models. We construct architectures that combine a classic model of ne… ▽ More Chaos is generic in strongly-coupled recurrent networks of model neurons, and thought to be an easily accessible dynamical regime in the brain. While neural chaos is typically seen as an impediment to robust computation, we show how such chaos might play a functional role in allowing the brain to learn and sample from generative models. We construct architectures that combine a classic model of neural chaos either with a canonical generative modeling architecture or with energy-based models of neural memory. We show that these architectures have appealing properties for sampling, including easy biologically-plausible control of sampling rates via overall gain modulation. △ Less

Submitted 26 September, 2024; originally announced September 2024.

Automated Question Generation on Tabular Data for Conversational Data Exploration

Authors: Ritwik Chaudhuri, Rajmohan C, Kirushikesh DB, Arvind Agarwal

Abstract: Exploratory data analysis (EDA) is an essential step for analyzing a dataset to derive insights. Several EDA techniques have been explored in the literature. Many of them leverage visualizations through various plots. But it is not easy to interpret them for a non-technical user, and producing appropriate visualizations is also tough when there are a large number of columns. Few other works provid… ▽ More Exploratory data analysis (EDA) is an essential step for analyzing a dataset to derive insights. Several EDA techniques have been explored in the literature. Many of them leverage visualizations through various plots. But it is not easy to interpret them for a non-technical user, and producing appropriate visualizations is also tough when there are a large number of columns. Few other works provide a view of some interesting slices of data but it is still difficult for the user to draw relevant insights from them. Of late, conversational data exploration is gaining a lot of traction among non-technical users. It helps the user to explore the dataset without having deep technical knowledge about the data. Towards this, we propose a system that recommends interesting questions in natural language based on relevant slices of a dataset in a conversational setting. Specifically, given a dataset, we pick a select set of interesting columns and identify interesting slices of such columns and column combinations based on few interestingness measures. We use our own fine-tuned variation of a pre-trained language model(T5) to generate natural language questions in a specific manner. We then slot-fill values in the generated questions and rank them for recommendations. We show the utility of our proposed system in a coversational setting with a collection of real datasets. △ Less

Submitted 10 July, 2024; originally announced July 2024.

Towards Reverse-Engineering the Brain: Brain-Derived Neuromorphic Computing Approach with Photonic, Electronic, and Ionic Dynamicity in 3D integrated circuits

Authors: S. J. Ben Yoo, Luis El-Srouji, Suman Datta, Shimeng Yu, Jean Anne Incorvia, Alberto Salleo, Volker Sorger, Juejun Hu, Lionel C Kimerling, Kristofer Bouchard, Joy Geng, Rishidev Chaudhuri, Charan Ranganath, Randall O'Reilly

Abstract: The human brain has immense learning capabilities at extreme energy efficiencies and scale that no artificial system has been able to match. For decades, reverse engineering the brain has been one of the top priorities of science and technology research. Despite numerous efforts, conventional electronics-based methods have failed to match the scalability, energy efficiency, and self-supervised lea… ▽ More The human brain has immense learning capabilities at extreme energy efficiencies and scale that no artificial system has been able to match. For decades, reverse engineering the brain has been one of the top priorities of science and technology research. Despite numerous efforts, conventional electronics-based methods have failed to match the scalability, energy efficiency, and self-supervised learning capabilities of the human brain. On the other hand, very recent progress in the development of new generations of photonic and electronic memristive materials, device technologies, and 3D electronic-photonic integrated circuits (3D EPIC ) promise to realize new brain-derived neuromorphic systems with comparable connectivity, density, energy-efficiency, and scalability. When combined with bio-realistic learning algorithms and architectures, it may be possible to realize an 'artificial brain' prototype with general self-learning capabilities. This paper argues the possibility of reverse-engineering the brain through architecting a prototype of a brain-derived neuromorphic computing system consisting of artificial electronic, ionic, photonic materials, devices, and circuits with dynamicity resembling the bio-plausible molecular, neuro/synaptic, neuro-circuit, and multi-structural hierarchical macro-circuits of the brain based on well-tested computational models. We further argue the importance of bio-plausible local learning algorithms applicable to the neuromorphic computing system that capture the flexible and adaptive unsupervised and self-supervised learning mechanisms central to human intelligence. Most importantly, we emphasize that the unique capabilities in brain-derived neuromorphic computing prototype systems will enable us to understand links between specific neuronal and network-level properties with system-level functioning and behavior. △ Less

Submitted 28 March, 2024; originally announced March 2024.

Comments: 15 pages, 12 figures

ProtoBandit: Efficient Prototype Selection via Multi-Armed Bandits

Authors: Arghya Roy Chaudhuri, Pratik Jawanpuria, Bamdev Mishra

Abstract: In this work, we propose a multi-armed bandit-based framework for identifying a compact set of informative data instances (i.e., the prototypes) from a source dataset $S$ that best represents a given target set $T$. Prototypical examples of a given dataset offer interpretable insights into the underlying data distribution and assist in example-based reasoning, thereby influencing every sphere of h… ▽ More In this work, we propose a multi-armed bandit-based framework for identifying a compact set of informative data instances (i.e., the prototypes) from a source dataset $S$ that best represents a given target set $T$. Prototypical examples of a given dataset offer interpretable insights into the underlying data distribution and assist in example-based reasoning, thereby influencing every sphere of human decision-making. Current state-of-the-art prototype selection approaches require $O(|S||T|)$ similarity comparisons between source and target data points, which becomes prohibitively expensive for large-scale settings. We propose to mitigate this limitation by employing stochastic greedy search in the space of prototypical examples and multi-armed bandits for reducing the number of similarity comparisons. Our randomized algorithm, ProtoBandit, identifies a set of $k$ prototypes incurring $O(k^3|S|)$ similarity comparisons, which is independent of the size of the target set. An interesting outcome of our analysis is for the $k$-medoids clustering problem $T = S$ setting) in which we show that our algorithm ProtoBandit approximates the BUILD step solution of the partitioning around medoids (PAM) method in $O(k^3|S|)$ complexity. Empirically, we observe that ProtoBandit reduces the number of similarity computation calls by several orders of magnitudes ($100-1000$ times) while obtaining solutions similar in quality to those from state-of-the-art approaches. △ Less

Submitted 23 August, 2023; v1 submitted 4 October, 2022; originally announced October 2022.

Comments: Erratum corrected

Preventing Outages under Coordinated Cyber-Physical Attack with Secured PMUs

Authors: Yudi Huang, Ting He, Nilanjan Ray Chaudhuri, Thomas La Porta

Abstract: Due to the potentially severe consequences of coordinated cyber-physical attacks (CCPA), the design of defenses has gained significant attention. A popular approach is to eliminate the existence of attacks by either securing existing sensors or deploying secured PMUs. In this work, we improve this approach by lowering the defense target from eliminating attacks to preventing outages and reducing t… ▽ More Due to the potentially severe consequences of coordinated cyber-physical attacks (CCPA), the design of defenses has gained significant attention. A popular approach is to eliminate the existence of attacks by either securing existing sensors or deploying secured PMUs. In this work, we improve this approach by lowering the defense target from eliminating attacks to preventing outages and reducing the required number of PMUs. To this end, we formulate the problem of PMU Placement for Outage Prevention (PPOP) under DC power flow model as a tri-level non-linear optimization problem and transform it into a bi-level mixed-integer linear programming (MILP) problem. Then, we propose an alternating optimization framework to solve PPOP by iteratively adding constraints, for which we develop two constraint generation algorithms. In addition, for large-scale grids, we propose a polynomial-time heuristic algorithm to obtain suboptimal solutions. Next, we extend our solution to achieve the defense goal under AC power flow model. Finally, we evaluate our algorithm on IEEE 30-bus, 57-bus, 118-bus, and 300-bus systems, which demonstrates the potential of the proposed approach in greatly reducing the required number of PMUs. △ Less

Submitted 25 March, 2022; originally announced March 2022.

Verifiable Failure Localization in Smart Grid under Cyber-Physical Attacks

Authors: Yudi Huang, Ting He, Nilanjan Ray Chaudhuri, Thomas La Porta

Abstract: Cyber-physical attacks impose a significant threat to the smart grid, as the cyber attack makes it difficult to identify the actual damage caused by the physical attack. To defend against such attacks, various inference-based solutions have been proposed to estimate the states of grid elements (e.g., transmission lines) from measurements outside the attacked area, out of which a few have provided… ▽ More Cyber-physical attacks impose a significant threat to the smart grid, as the cyber attack makes it difficult to identify the actual damage caused by the physical attack. To defend against such attacks, various inference-based solutions have been proposed to estimate the states of grid elements (e.g., transmission lines) from measurements outside the attacked area, out of which a few have provided theoretical conditions for guaranteed accuracy. However, these conditions are usually based on the ground truth states and thus not verifiable in practice. To solve this problem, we develop (i) verifiable conditions that can be tested based on only observable information, and (ii) efficient algorithms for verifying the states of links (i.e., transmission lines) within the attacked area based on these conditions. Our numerical evaluations based on the Polish power grid and IEEE 300-bus system demonstrate that the proposed algorithms are highly successful in verifying the states of truly failed links, and can thus greatly help in prioritizing repairs during the recovery process. △ Less

Submitted 18 January, 2021; originally announced January 2021.

Using noise to probe recurrent neural network structure and prune synapses

Authors: Eli Moore, Rishidev Chaudhuri

Abstract: Many networks in the brain are sparsely connected, and the brain eliminates synapses during development and learning. How could the brain decide which synapses to prune? In a recurrent network, determining the importance of a synapse between two neurons is a difficult computational problem, depending on the role that both neurons play and on all possible pathways of information flow between them.… ▽ More Many networks in the brain are sparsely connected, and the brain eliminates synapses during development and learning. How could the brain decide which synapses to prune? In a recurrent network, determining the importance of a synapse between two neurons is a difficult computational problem, depending on the role that both neurons play and on all possible pathways of information flow between them. Noise is ubiquitous in neural systems, and often considered an irritant to be overcome. Here we suggest that noise could play a functional role in synaptic pruning, allowing the brain to probe network structure and determine which synapses are redundant. We construct a simple, local, unsupervised plasticity rule that either strengthens or prunes synapses using only synaptic weight and the noise-driven covariance of the neighboring neurons. For a subset of linear and rectified-linear networks, we prove that this rule preserves the spectrum of the original matrix and hence preserves network dynamics even when the fraction of pruned synapses asymptotically approaches 1. The plasticity rule is biologically-plausible and may suggest a new role for noise in neural computation. △ Less

Submitted 16 July, 2021; v1 submitted 14 November, 2020; originally announced November 2020.

Journal ref: Advances in Neural Information Processing Systems 33 (NeurIPS 2020)

Power Grid State Estimation under General Cyber-Physical Attacks

Authors: Yudi Huang, Ting He, Nilanjan Ray Chaudhuri, Thomas La Porta

Abstract: Effective defense against cyber-physical attacks in power grid requires the capability of accurate damage assessment within the attacked area. While some solutions have been proposed to recover the phase angles and the link status (i.e., breaker status) within the attacked area, existing solutions made the limiting assumption that the grid stays connected after the attack. To fill this gap, we stu… ▽ More Effective defense against cyber-physical attacks in power grid requires the capability of accurate damage assessment within the attacked area. While some solutions have been proposed to recover the phase angles and the link status (i.e., breaker status) within the attacked area, existing solutions made the limiting assumption that the grid stays connected after the attack. To fill this gap, we study the problem of recovering the phase angles and the link status under a general cyber-physical attack that may partition the grid into islands. To this end, we (i) show that the existing solutions and recovery conditions still hold if the post-attack power injections in the attacked area are known, and (ii) propose a linear programming-based algorithm that can perfectly recover the link status under certain conditions even if the post-attack power injections are unknown. Our numerical evaluations based on the Polish power grid demonstrate that the proposed algorithm is highly accurate in localizing failed links once the phase angles are known. △ Less

Submitted 4 February, 2021; v1 submitted 4 September, 2020; originally announced September 2020.

Comments: Assumptions clarified; proof revised

Fine-Grained Stochastic Architecture Search

Authors: Shraman Ray Chaudhuri, Elad Eban, Hanhan Li, Max Moroz, Yair Movshovitz-Attias

Abstract: State-of-the-art deep networks are often too large to deploy on mobile devices and embedded systems. Mobile neural architecture search (NAS) methods automate the design of small models but state-of-the-art NAS methods are expensive to run. Differentiable neural architecture search (DNAS) methods reduce the search cost but explore a limited subspace of candidate architectures. In this paper, we int… ▽ More State-of-the-art deep networks are often too large to deploy on mobile devices and embedded systems. Mobile neural architecture search (NAS) methods automate the design of small models but state-of-the-art NAS methods are expensive to run. Differentiable neural architecture search (DNAS) methods reduce the search cost but explore a limited subspace of candidate architectures. In this paper, we introduce Fine-Grained Stochastic Architecture Search (FiGS), a differentiable search method that searches over a much larger set of candidate architectures. FiGS simultaneously selects and modifies operators in the search space by applying a structured sparse regularization penalty based on the Logistic-Sigmoid distribution. We show results across 3 existing search spaces, matching or outperforming the original search algorithms and producing state-of-the-art parameter-efficient models on ImageNet (e.g., 75.4% top-1 with 2.6M params). Using our architectures as backbones for object detection with SSDLite, we achieve significantly higher mAP on COCO (e.g., 25.8 with 3.0M params) than MobileNetV3 and MnasNet. △ Less

Submitted 16 June, 2020; originally announced June 2020.

Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning

Authors: Alexandros Papadopoulos, Konstantinos Kyritsis, Lisa Klingelhoefer, Sevasti Bostanjopoulou, K. Ray Chaudhuri, Anastasios Delopoulos

Abstract: Parkinson's Disease (PD) is a slowly evolving neuro-logical disease that affects about 1% of the population above 60 years old, causing symptoms that are subtle at first, but whose intensity increases as the disease progresses. Automated detection of these symptoms could offer clues as to the early onset of the disease, thus improving the expected clinical outcomes of the patients via appropriatel… ▽ More Parkinson's Disease (PD) is a slowly evolving neuro-logical disease that affects about 1% of the population above 60 years old, causing symptoms that are subtle at first, but whose intensity increases as the disease progresses. Automated detection of these symptoms could offer clues as to the early onset of the disease, thus improving the expected clinical outcomes of the patients via appropriately targeted interventions. This potential has led many researchers to develop methods that use widely available sensors to measure and quantify the presence of PD symptoms such as tremor, rigidity and braykinesia. However, most of these approaches operate under controlled settings, such as in lab or at home, thus limiting their applicability under free-living conditions. In this work, we present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device. We propose a Multiple-Instance Learning approach, wherein a subject is represented as an unordered bag of accelerometer signal segments and a single, expert-provided, tremor annotation. Our method combines deep feature learning with a learnable pooling stage that is able to identify key instances within the subject bag, while still being trainable end-to-end. We validate our algorithm on a newly introduced dataset of 45 subjects, containing accelerometer signals collected entirely in-the-wild. The good classification performance obtained in the conducted experiments suggests that the proposed method can efficiently navigate the noisy environment of in-the-wild recordings. △ Less

Submitted 6 May, 2020; originally announced May 2020.

Regret Minimisation in Multi-Armed Bandits Using Bounded Arm Memory

Authors: Arghya Roy Chaudhuri, Shivaram Kalyanakrishnan

Abstract: In this paper, we propose a constant word (RAM model) algorithm for regret minimisation for both finite and infinite Stochastic Multi-Armed Bandit (MAB) instances. Most of the existing regret minimisation algorithms need to remember the statistics of all the arms they encounter. This may become a problem for the cases where the number of available words of memory is limited. Designing an efficient… ▽ More In this paper, we propose a constant word (RAM model) algorithm for regret minimisation for both finite and infinite Stochastic Multi-Armed Bandit (MAB) instances. Most of the existing regret minimisation algorithms need to remember the statistics of all the arms they encounter. This may become a problem for the cases where the number of available words of memory is limited. Designing an efficient regret minimisation algorithm that uses a constant number of words has long been interesting to the community. Some early attempts consider the number of arms to be infinite, and require the reward distribution of the arms to belong to some particular family. Recently, for finitely many-armed bandits an explore-then-commit based algorithm~\citep{Liau+PSY:2018} seems to escape such assumption. However, due to the underlying PAC-based elimination their method incurs a high regret. We present a conceptually simple, and efficient algorithm that needs to remember statistics of at most $M$ arms, and for any $K$-armed finite bandit instance it enjoys a $O(KM +K^{1.5}\sqrt{T\log (T/MK)}/M)$ upper-bound on regret. We extend it to achieve sub-linear \textit{quantile-regret}~\citep{RoyChaudhuri+K:2018} and empirically verify the efficiency of our algorithm via experiments. △ Less

Submitted 24 January, 2019; originally announced January 2019.

PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits

Authors: Arghya Roy Chaudhuri, Shivaram Kalyanakrishnan

Abstract: We consider the problem of identifying any $k$ out of the best $m$ arms in an $n$-armed stochastic multi-armed bandit. Framed in the PAC setting, this particular problem generalises both the problem of `best subset selection' and that of selecting `one out of the best m' arms [arcsk 2017]. In applications such as crowd-sourcing and drug-designing, identifying a single good solution is often not su… ▽ More We consider the problem of identifying any $k$ out of the best $m$ arms in an $n$-armed stochastic multi-armed bandit. Framed in the PAC setting, this particular problem generalises both the problem of `best subset selection' and that of selecting `one out of the best m' arms [arcsk 2017]. In applications such as crowd-sourcing and drug-designing, identifying a single good solution is often not sufficient. Moreover, finding the best subset might be hard due to the presence of many indistinguishably close solutions. Our generalisation of identifying exactly $k$ arms out of the best $m$, where $1 \leq k \leq m$, serves as a more effective alternative. We present a lower bound on the worst-case sample complexity for general $k$, and a fully sequential PAC algorithm, \GLUCB, which is more sample-efficient on easy instances. Also, extending our analysis to infinite-armed bandits, we present a PAC algorithm that is independent of $n$, which identifies an arm from the best $ρ$ fraction of arms using at most an additive poly-log number of samples than compared to the lower bound, thereby improving over [arcsk 2017] and [Aziz+AKA:2018]. The problem of identifying $k > 1$ distinct arms from the best $ρ$ fraction is not always well-defined; for a special class of this problem, we present lower and upper bounds. Finally, through a reduction, we establish a relation between upper bounds for the `one out of the best $ρ$' problem for infinite instances and the `one out of the best $m$' problem for finite instances. We conjecture that it is more efficient to solve `small' finite instances using the latter formulation, rather than going through the former. △ Less

Submitted 24 January, 2019; originally announced January 2019.

Cogniculture: Towards a Better Human-Machine Co-evolution

Authors: Rakesh R Pimplikar, Kushal Mukherjee, Gyana Parija, Harit Vishwakarma, Ramasuri Narayanam, Sarthak Ahuja, Rohith D Vallam, Ritwik Chaudhuri, Joydeep Mondal

Abstract: Research in Artificial Intelligence is breaking technology barriers every day. New algorithms and high performance computing are making things possible which we could only have imagined earlier. Though the enhancements in AI are making life easier for human beings day by day, there is constant fear that AI based systems will pose a threat to humanity. People in AI community have diverse set of opi… ▽ More Research in Artificial Intelligence is breaking technology barriers every day. New algorithms and high performance computing are making things possible which we could only have imagined earlier. Though the enhancements in AI are making life easier for human beings day by day, there is constant fear that AI based systems will pose a threat to humanity. People in AI community have diverse set of opinions regarding the pros and cons of AI mimicking human behavior. Instead of worrying about AI advancements, we propose a novel idea of cognitive agents, including both human and machines, living together in a complex adaptive ecosystem, collaborating on human computation for producing essential social goods while promoting sustenance, survival and evolution of the agents' life cycle. We highlight several research challenges and technology barriers in achieving this goal. We propose a governance mechanism around this ecosystem to ensure ethical behaviors of all cognitive agents. Along with a novel set of use-cases of Cogniculture, we discuss the road map ahead for this journey. △ Less

Submitted 11 December, 2017; originally announced December 2017.

Associative content-addressable networks with exponentially many robust stable states

Authors: Rishidev Chaudhuri, Ila Fiete

Abstract: The brain must robustly store a large number of memories, corresponding to the many events encountered over a lifetime. However, the number of memory states in existing neural network models either grows weakly with network size or recall fails catastrophically with vanishingly little noise. We construct an associative content-addressable memory with exponentially many stable states and robust err… ▽ More The brain must robustly store a large number of memories, corresponding to the many events encountered over a lifetime. However, the number of memory states in existing neural network models either grows weakly with network size or recall fails catastrophically with vanishingly little noise. We construct an associative content-addressable memory with exponentially many stable states and robust error-correction. The network possesses expander graph connectivity on a restricted Boltzmann machine architecture. The expansion property allows simple neural network dynamics to perform at par with modern error-correcting codes. Appropriate networks can be constructed with sparse random connections, glomerular nodes, and associative learning using low dynamic-range weights. Thus, sparse quasi-random structures---characteristic of important error-correcting codes---may provide for high-performance computation in artificial neural networks and the brain. △ Less

Submitted 2 November, 2017; v1 submitted 6 April, 2017; originally announced April 2017.

Comments: 42 pages, 8 figures

Deep Tensor Convolution on Multicores

Authors: David Budden, Alexander Matveev, Shibani Santurkar, Shraman Ray Chaudhuri, Nir Shavit

Abstract: Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to the low memory ceiling of GPU hardware. Existing CPU implementations overcome this constraint but are impractically slow. Here we extend and optimize the faster W… ▽ More Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to the low memory ceiling of GPU hardware. Existing CPU implementations overcome this constraint but are impractically slow. Here we extend and optimize the faster Winograd-class of convolutional algorithms to the $N$-dimensional case and specifically for CPU hardware. First, we remove the need to manually hand-craft algorithms by exploiting the relaxed constraints and cheap sparse access of CPU memory. Second, we maximize CPU utilization and multicore scalability by transforming data matrices to be cache-aware, integer multiples of AVX vector widths. Treating 2-dimensional ConvNets as a special (and the least beneficial) case of our approach, we demonstrate a 5 to 25-fold improvement in throughput compared to previous state-of-the-art. △ Less

Submitted 11 June, 2017; v1 submitted 20 November, 2016; originally announced November 2016.

Comments: 11 pages, 4 figures, 1 supplementary doc

A Novel Session Based Dual Steganographic Technique Using DWT and Spread Spectrum

Authors: Tanmay Bhattacharya, Nilanjan Dey, S. R. Bhadra Chaudhuri

Abstract: This paper proposed a DWT based Steganographic technique. Cover image is decomposed into four sub bands using DWT. Two secret images are embedded within the HL and HH sub bands respectively. During embedding secret images are dispersed within each band using a pseudo random sequence and a Session key. Secret images are extracted using the session key and the size of the images. In this approach th… ▽ More This paper proposed a DWT based Steganographic technique. Cover image is decomposed into four sub bands using DWT. Two secret images are embedded within the HL and HH sub bands respectively. During embedding secret images are dispersed within each band using a pseudo random sequence and a Session key. Secret images are extracted using the session key and the size of the images. In this approach the stego image generated is of acceptable level of imperceptibility and distortion compared to the cover image and the overall security is high. △ Less

Submitted 1 September, 2012; originally announced September 2012.

Comments: 5 pages, 9 figures. arXiv admin note: substantial text overlap with arXiv:1208.0803

Journal ref: International Journal of Modern Engineering Research (IJMER),Vol.1, Dec 2011, Issue1, pp-157-161,ISSN: 2249-6645

A Session based Multiple Image Hiding Technique using DWT and DCT

Authors: Tanmay Bhattacharya, Nilanjan Dey, S. R. Bhadra Chaudhuri

Abstract: This work proposes Steganographic technique for hiding multiple images in a color image based on DWT and DCT. The cover image is decomposed into three separate color planes namely R, G and B. Individual planes are decomposed into subbands using DWT. DCT is applied in HH component of each plane. Secret images are dispersed among the selected DCT coefficients using a pseudo random sequence and a Ses… ▽ More This work proposes Steganographic technique for hiding multiple images in a color image based on DWT and DCT. The cover image is decomposed into three separate color planes namely R, G and B. Individual planes are decomposed into subbands using DWT. DCT is applied in HH component of each plane. Secret images are dispersed among the selected DCT coefficients using a pseudo random sequence and a Session key. Secret images are extracted using the session key and the size of the images from the planer decomposed stego image. In this approach the stego image generated is of acceptable level of imperceptibility and distortion compared to the cover image and the overall security is high. △ Less

Submitted 4 August, 2012; originally announced August 2012.

Comments: 4 pages,16 figures, "Published with International Journal of Computer Applications (IJCA)"

Journal ref: Tanmay Bhattacharya,Nilanjan Dey,Bhadra S R Chaudhuri. Article:A Session Based Multiple Image Hiding Technique using DWT&DCT.International Journal of Computer Applications 38(5):18-21,January 2012.Published by Foundation of Computer Science

Design and Fabrication of Micromachined Resonators

Authors: Ritesh Ray Chaudhuri, Joydeep Basu, Tarun Kanti Bhattacharyya

Abstract: Microelectromechanical system (MEMS) based on-chip resonators offer great potential for sensing and high frequency signal processing applications due to their exceptional features like small size, large frequency-quality factor product, integrability with CMOS ICs, low power consumption etc. This work is mainly aimed at the design, modeling, simulation, and fabrication of micromachined polysilicon… ▽ More Microelectromechanical system (MEMS) based on-chip resonators offer great potential for sensing and high frequency signal processing applications due to their exceptional features like small size, large frequency-quality factor product, integrability with CMOS ICs, low power consumption etc. This work is mainly aimed at the design, modeling, simulation, and fabrication of micromachined polysilicon disk resonators exhibiting radial-contour mode vibrations. A few other bulk mode modified resonator geometries are also being explored. The resonator structures have been designed and simulated in CoventorWare finite-element platform and fabricated by the PolyMUMPs surface micromachining process. △ Less

Submitted 14 February, 2012; originally announced February 2012.

Comments: 7 pages, 12 figures

Journal ref: Proceedings of the 6th International Conference on Smart Materials, Structures and Systems, January 04-07, 2012, Bangalore, India