Enter inventor name

White Plains, NY, United States of America

Chia-Yu Chen

This inventor holds 61 USPTO granted patents and 6 published patent applications, primarily in Machine Learning Hardware (CPC class H01L). Top assignees: International Business Machines Corporation, Globalfoundries Inc., National Tsing Hua University. Active years: 2016-2025.

USPTO Granted Patents = 61 (Patent Applications = 6)

% Patents Active = 63.9

Average Co-Inventor Count = 4.2

ph-index = 4

Forward Citations = 76(Granted Patents)

Forward Citations (Not Self Cited) = 64(Dec 10, 2025)

Inventors with similar research interests:

Location History:

Guilderland, NY (US) (2016 - 2017)
Yorktown Heights, NY (US) (2016 - 2023)
White Plains, NY (US) (2016 - 2024)
Westchester, NY (US) (2020 - 2024)

Company Filing History:

59 out of 166,159

International Business Machines Corporation

National Tsing Hua University

patents

where one patent can have more than one assignee

Years Active: 2016-2025

Loading Chart...

Areas of Expertise:

Deep Learning Inference

Adversarial Robustness

Matrix Multiplication

Neural Network Circuitry

Gradient Weight Compression

Symbolic Sequence Analytics

Systolic Array

Asynchronous Gradient

Noise Generation

CMOS Integration

True Random Generator

Dataflow Architecture

61 patents (USPTO):Sort by Forward CitationsExplore Patents

1. 12443841 - Four-bit training for machine learning (2025-10-14),

2. 12261619 - Stochastic rounding switched capacitor computation cores useful for efficient deep learning inference (2025-03-25),

3. 12217158 - Neural network circuitry having floating point format with asymmetric range (2025-02-04),

4. 12182274 - Testing adversarial robustness of systems with limited access (2024-12-31),

5. 12175359 - Machine learning hardware having reduced precision parameter components for efficient parameter update (2024-12-24),

6. 12141513 - Method to map convolutional layers of deep neural network on a plurality of processing elements with SIMD execution units, private memories, and connected as a 2D systolic processor array (2024-11-12),

7. 12061991 - Transfer learning with machine learning systems (2024-08-13),

8. 11977974 - Compression of fully connected / recurrent layers of deep network(s) through enforcing spatial locality to weight matrices and effecting frequency compression (2024-05-07),

9. 11853713 - Graph similarity analytics (2023-12-26),

10. 11836256 - Testing adversarial robustness of systems with limited access (2023-12-05),

11. 11816549 - Asynchronous gradient weight compression (2023-11-14),

12. 11797851 - Inference focus for offline training of SRAM inference engine in binary neural network (2023-10-24),

13. 11604647 - Mixed precision capable hardware for tuning a machine learning model (2023-03-14),

14. 11599785 - Inference focus for offline training of SRAM inference engine in binary neural network (2023-03-07),

15. 11586912 - Integrated noise generation for adversarial training (2023-02-21),

Title: The Innovations of Chia-Yu Chen: A Pioneer in Neural Network Technology

Introduction

Chia-Yu Chen is a prominent inventor based in White Plains, NY, with an impressive portfolio of 59 patents. His innovative work significantly contributes to the fields of neural networks and adversarial robustness testing, showcasing his expertise and commitment to technological advancement.

Latest Patents

Chia-Yu Chen's recent patents exemplify his groundbreaking approach to neural networks. One of his latest inventions is a "Neural network circuitry having floating point format with asymmetric range" which features circuitry designed to execute forward and backward propagation neural network operations using floating point numbers in distinct n-bit formats. This innovative design allows for improved efficiency in processing data, enhancing the performance of neural networks.

Another notable patent is focused on "Testing adversarial robustness of systems with limited access." This method provides a robust framework for assessing the resilience of black-box systems under various access conditions, enabling more effective and targeted testing strategies. These patents highlight Chen’s contributions to making neural networks both more versatile and secure in their applications.

Career Highlights

Chia-Yu Chen has amassed significant experience during his career, having worked with esteemed companies such as IBM and Globalfoundries Inc. His roles in these organizations have allowed him to push the boundaries of technology and contribute to cutting-edge research.

Collaborations

Collaboration has played a key role in Chia-Yu Chen's success as an inventor. He has had the opportunity to work alongside notable colleagues such as Tenko Yamashita and Zuoguang Liu. Together, they have nurtured an environment of innovation and creativity that has led to impactful advancements in their field.

Conclusion

Chia-Yu Chen stands out as a leading inventor whose work primarily revolves around neural networks and system robustness testing. His substantial number of patents and collaborations reflect a career dedicated to innovation and excellence. As technology continues to evolve, Chen's contributions are likely to remain influential, shaping the future of artificial intelligence and machine learning.

This text is generated by artificial intelligence and may not be accurate.

Please report any incorrect information to [email protected]