Patents by Inventor Boris Bonev

Boris Bonev has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • CONSTRAINING NEURAL NETWORK PARAMETER, ACTIVATION, AND GRADIENT DYNAMIC RANGE
    Publication number: 20260195579
    Abstract: Layer normalization within a neural network is replaced with scaling operations for stable optimization and reduced training time at a lower computational cost. The dynamic range of at least one of neural network parameters, activations, and/or gradients are constrained to a predetermined range to improve quantization and training stability without requiring calibration.
    Type: Application
    Filed: January 20, 2026
    Publication date: July 9, 2026
    Inventors: Matthijs Jules Van keirsbilck, Alexander Georg Keller, Nikolaus Binder, Tobias Zirr, Boris Bonev
  • INITIALIZATION FOR STABLE OPTIMIZATION OF SCALING RESIDUAL NEURAL NETWORKS
    Publication number: 20260195576
    Abstract: Layer normalization within a neural network is replaced with scaling operations to achieve the benefits of layer normalization (stable optimization and reduced training time) at a lower computational cost. Scaling parameters used by the scaling operations are initialized according to a calibration process and then learned during training (optimization).
    Type: Application
    Filed: April 30, 2025
    Publication date: July 9, 2026
    Inventors: Matthijs Jules Van keirsbilck, Alexander Georg Keller, Nikolaus Binder, Tobias Zirr, Boris Bonev