< BK21+ BEST Seminar Series Announcement> 

Time and Date : 16:00 ~ 17:00 Monday 11/26/2018

Place : B201, Engineering Building #2

Title : Machine Learning in Silicon

Abstract:

There is much interest in embedding data analytics and artificial intelligence capabilities into sensor-rich platforms such as wearables, biomedical devices, autonomous vehicles, robots, and the Internet of Things (IoT) to provide them with decision-making capabilities. Such platforms need to implement machine learning algorithms under severe resource constraints on embedded battery-powered platforms. On the other hand, such ML algorithms require processing of large data volumes, e.g., >100 M neurons for VGGNet.

As a result, there have been on-going effort to realize energy- and latency- efficient information processing. In this talk, recent research trend in machine learning accelerator architecture will be discussed including algorithm, circuit, and architecture level innovations. As an example of such implementation, deep in-memory architecture will be described in further detail by focusing its concept, design principles, challenges, and silicon-measured results.

Presenter: Min Koo Kang, Research Staff Member / IBM TJ Watson Research Center 

Host: Prof. Jung, Seong-ook, Yonsei EEE