Plenary Talk 5

  • 홈ˆ
  • Program
  • Plenary Talk 5

[Plenary Talk 5]    11.3(Fri) 09:30 - 11:00

James Kwok
HKUST, Hong Kong

Machine intelligence in a complicated world

▷ Abstract
Artificial intelligence is now widely used in both the physical world and social world, from personal assistants, self-driving cars, automated customer service to product recommendations. Consequently, the underlying machine learning tasks also vary from the more traditional classification/regression type of problems to the generation of realistic images, texts and audios. Depending on the amount of data/hardware available and the problem complexity, a large number of deep and non-deep learning models have been developed over the years. Domain-specific user preferences and problem characteristics can be incorporated by designing appropriate model structures and regularizers. Examples include the use of convolutional structures in image applications, and low-rank matrix regularizers in collaborative filtering applications. The resultant model often involves smooth/nonsmooth and convex/nonconvex components, making model inference difficult and computationally expensive. Moreover, with the increasing proliferation of the internet of things and wearable devices, deploying machine learning models onto these small computing devices imposes significant time and space limitations. In this talk, I will describe recent approaches that learn the deep and non-deep learning models efficiently, and also on compression deep learning models so that the network size can be reduced without sacrificing performance.

▷ Bio
Prof. Kwok is a Professor in the Department of Computer Science and Engineering, Hong Kong University of Science and Technology. He received his B.Sc. degree in Electrical and Electronic Engineering from the University of Hong Kong and his Ph.D. degree in computer science from the Hong Kong University of Science and Technology. Prof. Kwok served/is serving as an Associate Editor for the IEEE Transactions on Neural Networks and Learning Systems and the Neurocomputing journal. He has also served as Program Co-chair of a number of international conferences, and as Area Chairs in conferences such as NIPS, ICML, ECML and IJCAI. He is an IEEE Fellow.

※ The above schedule is subject to change.

서울시 서초구 방배로 76 (방배동, 머리재빌딩 401호) 우)06704 | (Tel)1588-2728 | (Fax)02-521-1352 | 사업자등록번호 : 114-82-03170 | 대표 : 나연묵

Copyright (c) KIISE. All rights reserved.