Cedar Park, TX, United States of America

Dave Fick

This inventor holds 1 USPTO granted patent. Top assignee: Mythic, Inc.. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Dave Fick. Retrieved from https://idiyas.com/inventor/dave-fick-ul4k8t2c

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile


Average Co-Inventor Count = 1.0


Company Filing History:


Years Active: 2026

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Dave Fick and Neural Network Hardware Optimization.

Introduction

Dave Fick is an inventor based in Cedar Park, Texas, and is associated with Mythic, Inc. His patent work concerns methods for preparing artificial neural networks for efficient execution on specialized hardware.

Latest Patents

Fick is named on 1 patent: “Systems and Methods for Intelligently Folding Normalization and Weight Parameters During a Training of an Artificial Neural Network.” The invention describes transforming a pre-trained network graph by replacing a computational node with a system-generated node that combines computational and normalization operations. During retraining, the system folds their parameters into integrated weight and bias matrices, updates and scales those parameters, and may scale output activations to improve signal-to-noise characteristics. It then generates a hardware-execution graph and compiles it into instructions for a matrix multiply accelerator or another integrated circuit.

Career Highlights

The patent reflects work at the intersection of neural network training, model optimization, and hardware execution. Its approach aims to integrate operations and parameters during retraining so that the resulting network can be compiled for specialized computing hardware.

Collaborations

The supplied information associates Fick with Mythic, Inc. The patent’s described system involves training and hardware compilation, but the provided details do not identify additional collaborators.

Conclusion

Dave Fick’s patent focuses on folding normalization and computational parameters during neural network training to support efficient execution on hardware accelerators.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…