New York, NY, United States of America

Leland Chang

This inventor holds 138 USPTO granted patents and 12 published patent applications, plus 1 CIPO patent and 2 EPO patents, primarily in Neural Network Technology (CPC class G06N3-063). Top assignees: International Business Machines Corporation, Globalfoundries Inc., Globalfoundries U.S. 2 LLC. Active years: 2002-2025.

USPTO Granted Patents = 138 

% Patents Active = 45.7


 

Average Co-Inventor Count = 3.7

ph-index = 17

Forward Citations = 2,083(Granted Patents)

Forward Citations (Not Self Cited) = 2,019(Dec 10, 2025)


Inventors with similar research interests:

🔬 See more inventors

Location History:

  • Berkeley, CA (US) (2002)
  • Yorktown, NY (US) (2011)
  • Yorktown Heights, NY (US) (2011 - 2014)
  • NY, NY (US) (2015)
  • New York, NY (US) (2006 - 2024)

Company Filing History:


Years Active: 2002-2025

Loading Chart...
Loading Chart...
Loading Chart...
Areas of Expertise:
Convolutional Neural Network
Deep Neural Network
Power Conversion
Voltage Regulation
Neurosynaptic Module
Hybrid FINFET
Reconfigurable Circuits
Dynamic Logic
Stochastic Perforation
Multi-Phase Buck Converter
Phantom Inductor
Moat Power Metallization
138 patents (USPTO):Explore Patents

Title: Leland Chang: Innovating the Future with Neurosynaptic Modules and Bi-Scaled Deep Neural Networks

Introduction:

Meet Leland Chang, a prolific inventor based in New York, NY. With an impressive number of 135 patents to his name, Chang has made significant contributions in the fields of neurosynaptic modules and deep neural networks. His latest patents demonstrate his innovation in implementing neural networks through time-division multiplexing with implicit memory addressing and developing bi-scaled deep neural networks. Let's delve into Chang's latest patents, career highlights, and notable collaborations.

Latest Patents:

1. Time-division multiplexed neurosynaptic module with implicit memory addressing for implementing a neural network:

Chang's inventive breakthrough in this patent involves a time-division multiplexed neurosynaptic module that employs implicit memory addressing to implement a neural network. By integrating incoming firing events in a time-division multiplexing manner, this technology allows for efficient computing and parallel updating of neuron attributes. The patent describes a novel approach to improve the performance and capabilities of neural networks.

2. Bi-scaled deep neural networks:

In this patent, Chang introduces a method for creating deep neural networks (DNN) by quantizing deep learning data structures into multiple modes, each associated with a specific scale factor. Determining the appropriate scale factor for each data structure is based on the distribution of the data. The use of bi-scaled structures optimizes the efficiency of DNNs and improves their ability to handle diverse data sets.

Career Highlights:

Leland Chang has an extensive background working with renowned companies in the technology industry. Some of his notable career highlights include:

1. International Business Machines Corporation (IBM):

Chang has played an instrumental role at IBM, a global technology company. IBM is known for its groundbreaking innovations in computing and technology solutions. Chang's involvement with IBM highlights his commitment to pushing the boundaries of artificial intelligence and neural networks.

2. GlobalFoundries Inc.:

Another significant collaboration in Chang's career is with GlobalFoundries Inc., a leading semiconductor manufacturing company. Chang's work with GlobalFoundries showcases his expertise in developing advanced technologies that power numerous electronic devices.

Collaborations:

Leland Chang has had the privilege of working alongside esteemed colleagues throughout his career. Notable collaborations include:

1. Jeffrey W Sleight:

Chang has collaborated with Jeffrey W Sleight, a distinguished innovator, in driving forward advancements in the neurosynaptic module field and neural network implementations. Their collaborations have contributed to the development of novel techniques and technologies that have the potential to revolutionize the way we use neural networks.

2. Josephine B Chang:

Josephine B Chang is another colleague with whom Leland Chang has worked closely. Their collaborations have focused on bi-scaled deep neural networks, pushing the boundaries of data quantization techniques and enhancing the performance of deep learning processes.

Conclusion:

Leland Chang's dedication to innovation and his exceptional patent record in neurosynaptic modules and deep neural networks highlight his significant contributions to the field. With his latest patents, Chang continues to innovate and shape the future of artificial intelligence. His collaborations with renowned companies and colleagues reinforce his reputation as an inspiring and accomplished inventor. We can't wait to see what groundbreaking technologies Leland Chang will bring to the world in the future.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to [email protected]
Loading…