Andre Chang

Title: Innovations of Andre Chang in Convolutional Neural Networks

Introduction

Andre Chang is an accomplished inventor based in West Lafayette, Indiana. She has made significant contributions to the field of artificial intelligence, particularly in the area of convolutional neural networks (CNNs). Her innovative work has led to the development of a unique hardware accelerator designed to enhance the processing capabilities of CNNs.

Latest Patents

Andre Chang holds a patent for a "Hardware accelerator for convolutional neural networks and method of operation thereof." This patent describes an accelerator that includes a compute core with multiple compute units. Each compute unit is equipped with a first memory cache for storing vectors in a map trace and a second memory cache for vectors in a kernel trace. The architecture also features vector multiply-accumulate units (vMACs) that are connected to these memory caches. Each vMAC contains several multiply-accumulate units (MACs), which perform complex calculations to improve the efficiency of CNN processing.

Career Highlights

Chang is associated with the Purdue Research Foundation, where she continues to push the boundaries of technology and innovation. Her work is instrumental in advancing the capabilities of machine learning and artificial intelligence applications.

Collaborations

Andre collaborates with notable colleagues, including Eugenio Culurciello and Vinayak Anand Gokhale. Their combined expertise fosters a dynamic research environment that promotes groundbreaking advancements in technology.

Conclusion

Andre Chang's contributions to the field of convolutional neural networks exemplify the impact of innovative thinking in technology. Her patent and ongoing work at Purdue Research Foundation highlight her role as a leading inventor in this critical area of research.