Hyesun Hong

Title: Hyesun Hong: Innovator in Electronic Devices and Deep Learning

Introduction

Hyesun Hong is a prominent inventor based in Suwon-si, South Korea. He has made significant contributions to the field of electronic devices and deep learning technologies. With a total of 3 patents, his work showcases innovative approaches to complex computational problems.

Latest Patents

Hyesun Hong's latest patents include an electronic device and method with compressed storage format conversion. This invention involves a host processor that converts a sparse matrix compressed in a first format into a second compressed storage format. The device preprocesses a vector based on this new format and transmits both the converted sparse matrix and the preprocessed vector to a computing device. The computing device is then configured to multiply the sparse matrix by the preprocessed vector. Another notable patent is a hybrid scheduling method for deep learning workloads, which includes a computing apparatus that generates an input vector with resource status and metadata for tasks. This method determines actions for resource scheduling, evaluates performance, and allocates resources efficiently.

Career Highlights

Hyesun Hong is currently employed at Samsung Electronics Co., Ltd., where he continues to push the boundaries of technology. His work at Samsung has allowed him to develop cutting-edge solutions that enhance the efficiency of electronic devices and deep learning applications.

Collaborations

Hyesun collaborates with talented individuals such as Peter Morris and Jinseong Kim. Their combined expertise contributes to the innovative projects at Samsung Electronics.

Conclusion

Hyesun Hong's contributions to electronic devices and deep learning exemplify the spirit of innovation. His patents reflect a commitment to advancing technology and improving computational efficiency.