Gi Ju Jung

Title: Gi Ju Jung: Innovator in ReRAM-Based Deep Learning Accelerators

Introduction

Gi Ju Jung is a notable inventor based in Ulsan, South Korea. He has made significant contributions to the field of deep learning accelerators, particularly through his innovative work on resistive random access memory (ReRAM). His expertise in this area has led to the development of a unique patent that addresses critical challenges in deep learning technology.

Latest Patents

Gi Ju Jung holds a patent titled "Stuck-at fault mitigation method for ReRAM-based deep learning accelerators." This patent presents a method for confirming a distorted output value (Y0) caused by a stuck-at fault (SAF) using a correction data set in a pre-trained deep learning network. The method involves updating the average (μ) and standard deviation (σ) of a batch normalization (BN) layer using the distorted output value (Y0). Furthermore, it details the process of folding the BN layer into a convolution layer or a fully-connected layer and deriving a normal output value (Y1) through the deep learning network.

Career Highlights

Throughout his career, Gi Ju Jung has worked at prestigious institutions, including King Abdullah University of Science and Technology and the University of California. His experience in these environments has allowed him to collaborate with leading experts in the field and contribute to groundbreaking research.

Collaborations

Some of his notable coworkers include Ahmed Mohamed Eltawil and Mohammed Fouda. Their collaborative efforts have further advanced the research and development of deep learning technologies.

Conclusion

Gi Ju Jung's innovative work in the realm of ReRAM-based deep learning accelerators showcases his commitment to advancing technology. His patent reflects a significant step forward in addressing challenges within the field, and his collaborations with esteemed colleagues highlight the importance of teamwork in driving innovation.