日　時： 7月13日（火） 15:10-16:40
会　場： オンライン開催
題　目： 先端人工知能論I 特別講演
講師名： David Ha氏（Google Brain Team）

Title: The Role of World Models and Abstraction for Neural Network Agents

Abstract: In the past decade we saw great improvements in neural networks applied to machine learning. When combined with reinforcement learning, neural networks are able to learn tasks that were previously difficult with hand-engineered approaches. However, neural network policies are often brittle in nature and also do not generalize well beyond a narrow domain environment, like what we expect of humans. In this talk I will examine a line of work inspired by cognitive neuroscience, enabling artificial agents to possess a world model of its environment. I will examine the implications and explore future possibilities of such learnable world models and how they may affect agents able to exploit them.

Short bio: “David is a Research Scientist at Google Brain in Tokyo, Japan. His research interests include Neural Networks, Creative AI, and Evolutionary Computing. Prior to joining Google, He worked at Goldman Sachs as a Managing Director, where he ran the fixed-income trading business in Japan. He obtained undergraduate and graduate degrees in Engineering Science and Applied Math from the University of Toronto.

参加登録はこちら（https://forms.gle/ekv82djXj2Yswvck7）からお願いします。（締切： 7.13（火）12：00まで）
※登録できないなどの問題が生じた際は、 faire.ai.u.tokyo▲gmail.com (▲を@にかえて）まで、お問い合わせください。

※第1回：https://www.ai.u-tokyo.ac.jp/ja/activities/ai-seminar
※第2回：https://www.ai.u-tokyo.ac.jp/ja/activities/426