Jae Shin

Title: Innovations by Jae Shin in Convolutional Neural Networks

Introduction

Jae Shin is an accomplished inventor based in Phoenix, AZ, known for his significant contributions to the field of convolutional neural networks (CNNs). With a total of four patents to his name, he has developed innovative systems and methods that enhance the efficiency of medical imaging through advanced machine learning techniques.

Latest Patents

One of Jae Shin's latest patents focuses on "Systems, methods, and apparatuses for actively and continually fine-tuning convolutional neural networks to reduce annotation requirements." This invention addresses the challenges associated with creating large annotated datasets, which are essential for training CNNs. By integrating active learning and transfer learning into a single framework, his method significantly reduces the annotation cost and effort required for medical imaging applications. The evaluation of this method demonstrated a reduction in annotation efforts by at least half compared to random selection.

Another notable patent involves "Systems, methods, and/or media, for selecting candidates for annotation for use in training a classifier." This system is designed to select candidates for labeling, which are then used to train a CNN. It includes a memory device and a hardware processor that determines probabilities for unique patches of identically labeled candidates, ultimately enhancing the training process of the CNN.

Career Highlights

Jae Shin is currently affiliated with Arizona State University, where he continues to push the boundaries of research in machine learning and medical imaging. His work has garnered attention for its practical applications and innovative approaches to complex problems in the field.

Collaborations

Throughout his career, Jae has collaborated with notable colleagues, including Jianming Liang and Zongwei Zhou. These partnerships have contributed to the advancement of his research and the successful development of his patented technologies.

Conclusion

Jae Shin's innovative work in convolutional neural networks exemplifies the potential of machine learning to transform medical imaging. His patents not only address critical challenges in the field but also pave the way for future advancements in technology.