This inventor holds 1 USPTO granted patent. Top assignee: Ansys, Inc.. 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: Thomas Most and Neural Network Architecture Design.
Introduction
Thomas Most is an inventor based in Munich, Germany, associated with Ansys, Inc. His patent work concerns methods for designing artificial neural network architectures.
Latest Patents
Most is credited with 1 patent: “Automated Design of Architectures of Artificial Neural Networks.” The invention describes a method and apparatus for determining a reduced-space neural network architecture. A device receives a full-space architecture containing nodes and weights, transforms the weights, and uses them to reduce the nodes. It then creates a reduced-space architecture from the resulting nodes.
Career Highlights
The available information identifies Most’s work at Ansys, Inc. and highlights his contribution to neural network architecture design through this patent.
Collaborations
The listed coworkers associated with Most include Anas Abdulhkim Aburawwash Abdulhkim and Lars Gräning.
Conclusion
Thomas Most’s patent reflects work on reducing neural network architectures through transformed weights and node selection, connecting his inventive contribution with Ansys, Inc.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
