Practice Makes Perfect? A Machine's Perspective 從機器學習看「熟能生巧」
20200730.jpg

One ultimate goal of Artificial Intelligence (AI) is to build a machine/system that can learn by itself, via interactions with the environment. One successful example is AlphaGo, an AI that plays the board game Go with world-class performance. The underlying framework that builds AlphaGo is called Reinforcement Learning (RL), a standard paradigm where an AI can respond to the environment. In this lecture, we will study the idea of reinforcement learning and discuss how this framework can be applied to different applications such as digital marketing and game AI.

Date: 30 July 2020 (Thursday)
Time: 4:00pm - 5:00pm
Targets: F.4 to F.6 Students
Language: Cantonese
Instructor: Dr. Clint HO, Assistant Professor, School of Data Science, City University of Hong Kong