訊息公告

[專題演講] 敬邀參加2/13 (ㄧ) 10:00-11:00@ EC329 講者:Prof. Kenji Doya(Neural Computation Unit Okinawa Institute of Science and Technology)

Title: 
What Can We Further Learn From the Brain for AI and Robotics?
 
Abstract: 
Deep learning is a prime example of how brain-inspired computing can benefit AI and robotics. But what else can we learn from the brain for bringing AI and robotics to the next level? Energy efficiency and data efficiency are the major features of the brain and human cognition that today’s deep learning has yet to deliver. The brain can be seen as a multi-agent system of heterogeneous learners using different representations and algorithms. The flexible use of reactive, model-free control and model-based “mental simulation” appears to be the basis for computational and data efficiency of the brain. How the brain efficiently acquires and flexibly combines prediction and control modules is a major open problem in neuroscience and its solution should help developments of more flexible and autonomous AI and robotics.