30 April, 2019

HKSAIR-BDI Deep Learning Workshop was successfully held in HKUST

2019 HKSAIR-BDI Deep Learning Workshop was successfully held on 30th April in HKUST which was organized by the Hong Kong Society of Artificial Intelligence and Robotics (HK-SAIR) and co-organized by HKUST Big Data Institute (BDI).

Mr. Weiyan WANG and Mr. Han TIAN, postgraduate students of Prof Kai Chen, HKSAIR EC Member; Associate Professor of Department of Computer Science and Engineering (CSE) of HKUST, delivered this half-day practical workshop.

The workshop offered a deep understanding of the CNN model design and the method of how to build convolutional neural networks from scratch with Tensorflow2.0 then apply it to classify number images.

After showing the connection between the Support Vector Machine and Deep Neural Network, Mr. Weiyan WANG gave an introduction of CNN and interpreted it as the regularized form of MLP. Furthermore, he did the reviewing, comprising and analyzing through the different CNN milestones by following the timeline.

●Session 1: Diving into CNN

•Review: Linear Model and non-linear extension

•The evolution of different CNN network architectures

●Session 2: Hands-on Lab Tutorial • TensorFlow 2.0

•Recognize the hand-written characters

●Session 3: Q&A

During the second session, Mr. Han TIAN started with Tensorflow2.0 Alpha, an early version released, helping participants to try the new way to build an image classification model with several convolutional neural layers. TensorFlow 2.0 is a significant milestone and a major new release focusing on ease of use and simplification. With Keras tightly integrated and eager execution by default, it aligns users’ expectations about the programming model better with TensorFlow practice and should make TensorFlow easier to learn and apply.

The workshop was well-received with loads of questions raised by the attendees.

About HK-SAIR:

HK-SAIR is a non-profit organization, which focuses on Artificial Intelligence and Robotics (AIR) research and the AIR industry development. It cooperates with top universities and research committees in Hong Kong, making contributions to the innovations in Hong Kong’s financial industry, trade logistics, industrial manufacturing, supply chain, and other industries.

*Special thanks to Co.,Ltd. for providing the experimental platform.