Woongki Baek

Title: Woongki Baek: Innovator in Deep Learning and Memory Management

Introduction

Woongki Baek is a prominent inventor based in Ulsan, South Korea. He has made significant contributions to the fields of deep learning and memory management, holding a total of 5 patents. His innovative approaches have the potential to enhance the efficiency of embedded systems and virtual memory management.

Latest Patents

Among his latest patents is a method of slicing deep learning models for heterogeneous embedded systems. This method involves collecting execution time and power consumption data for each layer of a deep learning model across various computing devices. By predicting performance and power costs, as well as communication costs, the model slicing apparatus allocates different sliced layers to each device based on these metrics. Another notable patent is a method and device for dynamic adjustment of swapping in virtual memory management. This method adaptively adjusts the distribution state of memory based on the quality of service of tasks, optimizing the swap-out and swap-in processes for improved system efficiency.

Career Highlights

Woongki Baek has worked at the Ulsan National Institute of Science and Technology, contributing to cutting-edge research and development in his field. His work at this institution has allowed him to explore innovative solutions to complex problems in technology.

Collaborations

Throughout his career, Baek has collaborated with notable colleagues, including Myeonggyun Han and Seong Beom Park. These collaborations have fostered a productive environment for innovation and have led to advancements in their respective fields.

Conclusion

Woongki Baek's contributions to deep learning and memory management exemplify the spirit of innovation. His patents reflect a commitment to enhancing technology and improving system efficiencies. His work continues to influence the landscape of embedded systems and virtual memory management.