Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–3 of 3 results for author: Potempa, K

Searching in archive cs. Search in all archives.
.
  1. arXiv:2008.03936  [pdf, other

    cs.LG cs.NE math.RT stat.ML

    Intelligent Matrix Exponentiation

    Authors: Thomas Fischbacher, Iulia M. Comsa, Krzysztof Potempa, Moritz Firsching, Luca Versari, Jyrki Alakuijala

    Abstract: We present a novel machine learning architecture that uses the exponential of a single input-dependent matrix as its only nonlinearity. The mathematical simplicity of this architecture allows a detailed analysis of its behaviour, providing robustness guarantees via Lipschitz bounds. Despite its simplicity, a single matrix exponential layer already provides universal approximation properties and ca… ▽ More

    Submitted 10 August, 2020; originally announced August 2020.

    Comments: 20 pages, 10 figures

  2. arXiv:1908.03565  [pdf

    eess.IV cs.GR

    Committee Draft of JPEG XL Image Coding System

    Authors: Alexander Rhatushnyak, Jan Wassenberg, Jon Sneyers, Jyrki Alakuijala, Lode Vandevenne, Luca Versari, Robert Obryk, Zoltan Szabadka, Evgenii Kliuchnikov, Iulia-Maria Comsa, Krzysztof Potempa, Martin Bruse, Moritz Firsching, Renata Khasanova, Ruud van Asseldonk, Sami Boukortt, Sebastian Gomez, Thomas Fischbacher

    Abstract: JPEG XL is a practical approach focused on scalable web distribution and efficient compression of high-quality images. It provides various benefits compared to existing image formats: 60% size reduction at equivalent subjective quality; fast, parallelizable decoding and encoding configurations; features such as progressive, lossless, animation, and reversible transcoding of existing JPEG with 22%… ▽ More

    Submitted 13 August, 2019; v1 submitted 12 August, 2019; originally announced August 2019.

    Comments: Royalty-free, open-source reference implementation in Q4 2019. v3 fixes PDF links and paper size

    MSC Class: 94A08 ACM Class: I.4.2

  3. arXiv:1907.13223  [pdf, other

    cs.NE cs.LG q-bio.NC

    Temporal Coding in Spiking Neural Networks with Alpha Synaptic Function: Learning with Backpropagation

    Authors: Iulia M. Comsa, Krzysztof Potempa, Luca Versari, Thomas Fischbacher, Andrea Gesmundo, Jyrki Alakuijala

    Abstract: The timing of individual neuronal spikes is essential for biological brains to make fast responses to sensory stimuli. However, conventional artificial neural networks lack the intrinsic temporal coding ability present in biological networks. We propose a spiking neural network model that encodes information in the relative timing of individual neuron spikes. In classification tasks, the output of… ▽ More

    Submitted 16 November, 2020; v1 submitted 30 July, 2019; originally announced July 2019.

    Comments: Open-source code related to this paper is available at https://github.com/google/ihmehimmeli v2: Added references and added some clarifications for the methods