logo

For the Inventor, By the Inventor

San Jose, CA, United States of America

Andrew S Cassidy

This inventor holds 75 USPTO granted patents and 6 published patent applications and 1 EPO patent, primarily in Neural Network Technology (CPC class G06N). Top assignee: International Business Machines Corporation. Active years: 2015-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Andrew S Cassidy. Retrieved from https://idiyas.com/inventor/andrew-s-cassidy

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

Calculating rank
USPTO Granted Patents = 75 

% Patents Active = 61.3


Average Co-Inventor Count = 6.9

ph-index = 10

Forward Citations = 328(Granted Patents)

Forward Citations (Not Self Cited) = 292(Dec 10, 2025)


Inventors with similar research interests:


Location History:

  • San Jose, CA (US) (2015 - 2024)
  • Austin, TX (US) (2020 - 2024)

Company Filing History:

goldMedal75 out of 166,425 
 
International Business Machines Corporation
 patents

Years Active: 2015-2026

Loading Chart...
Loading Chart...
Areas of Expertise:
Neural Network Cores
Neurosynaptic Systems
Parallel Processing
Machine Learning
Inference Processing
VLSI Implementation
Data Distribution
Energy Efficiency
Memory Mapping
Event-Based Networks
Low-Power Design
Adaptive Architectures
75 patents (USPTO):Explore Patents
1. 12730644 - Selecting an executable operation from a lookup table identified by a conditional instruction and indexed based on combined results of concurrently-computed relational operators (2026-09-08),
2. 12670369 - Central scheduler and instruction dispatcher for a neural inference processor (2026-06-30),
3. 12481861 - Hierarchical parallelism in a network of distributed neural network cores (2025-11-25),
4. 12443830 - Compressed weight distribution in networks of neural processors (2025-10-14),
5. 12432229 - Detection of malicious encryption based on machine learning (2025-09-30),
6. 12406186 - Conflict-free, stall-free, broadcast network on chip (2025-09-02),
7. 12406174 - Multi-agent instruction execution engine for neural inference processing (2025-09-02),
8. 12400112 - Efficient method for VLSI implementation of useful neural network activation functions (2025-08-26),
9. 12400109 - Functional synthesis of networks of neurosynaptic cores on neuromorphic substrates (2025-08-26),
10. 12387082 - Scheduler for mapping neural networks onto an array of neural cores in an inference processing unit (2025-08-12),
11. 12182687 - Data representation for dynamic precision in neural network cores (2024-12-31),
12. 12165050 - Networks for distributing parameters and data to neural network compute cores (2024-12-10),
13. 12067472 - Defect resistant designs for location-sensitive neural network processor arrays (2024-08-20),
14. 12056598 - Runtime reconfigurable neural network processor core (2024-08-06),
15. 11847553 - Parallel computational architecture with reconfigurable core-level and vector-level parallelism (2023-12-19),

Title: Andrew S. Cassidy: Pioneering Innovations in Neural Network Technologies

Introduction

Andrew S. Cassidy is a prominent inventor based in San Jose, California, known for his significant contributions to the field of neural networks. With an impressive portfolio of 65 patents, Cassidy is at the forefront of innovation, primarily working at International Business Machines Corporation (IBM). His latest work focuses on enhancing the capabilities of neural network processors and computation systems.

Latest Patents

Among his recent patents, Cassidy has developed a groundbreaking technology for data representation that allows dynamic precision in neural network cores. This invention involves a neural network processor composed of multiple neural cores designed to process input data efficiently. The processor adapts to various precisions per activation and uses transformation circuits to ensure data is appropriately processed before conducting complex computations through the neural cores.

Additionally, Cassidy holds a patent related to networks for distributing parameters and data to neural network compute cores. This advancement includes the design of a neural inference chip that interconnects multiple neural cores. The innovation allows simultaneous delivery of synaptic weights and input activations, significantly improving the efficiency of neural computations and enhancing overall performance.

Career Highlights

Cassidy's career at IBM has been marked by a series of impactful inventions that have advanced the state of technology in neural computation. His deep understanding of both theoretical and practical applications of neural networks has led to multiple patents that address key challenges in the field. His work has not only contributed to IBM’s reputation as a leader in AI technology but has also paved the way for future innovations in neural processing.

Collaborations

Throughout his career, Cassidy has collaborated with esteemed colleagues such as Dharmendra S. Modha and John Vernon Arthur, who are also recognized for their contributions to the field of artificial intelligence and neural networks. These collaborations have led to numerous innovative projects, further establishing a dynamic research environment that fosters creative problem-solving and engineering excellence.

Conclusion

Andrew S. Cassidy is a trailblazer in the realm of neural network technologies, with a notable record of patents that reflect his ingenuity and commitment to innovation. As he continues his work at IBM, his contributions promise to shape the future of artificial intelligence and computing. His inventions not only enhance the capabilities of neural networks but also serve as a foundation for further advancements in the industry.

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…