This inventor holds 1 USPTO granted patent and 1 EPO patent. Top assignee: Commissariat a L'energie Atomique Et Aux Energies Alternatives. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Inna Kucher and Her Neural Network Training Patent.
Introduction
Inna Kucher is an inventor based in Gif-sur-Yvette, France. Her patent concerns a computer-implemented method for training synaptic weight values in an artificial neural network.
Latest Patents
Kucher is associated with 1 patent: “Method for Learning Synaptic Weight Values of a Neural Network, Related Data Processing Method, Computer Program, Calculator and Processing System.” The invention trains weight values using training data, with each trained weight selected from a set of quantized values. Those values are encoded using a predefined number of bits, and the quantization step between successive values follows a specified condition.
Career Highlights
Kucher’s listed company is the French Alternative Energies and Atomic Energy Commission (Commissariat à l’énergie atomique et aux énergies alternatives). Her patent focuses on quantized neural network weights and related data-processing implementations.
Collaborations
David Briand and Olivier Bichler are identified as Kucher’s coworkers.
Conclusion
Inna Kucher’s patent documents work on a computer-implemented approach to training quantized synaptic weights for artificial neural networks.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile