Multidisciplinary Institute in Artificial intelligence

What can we further learn from the brain for AI?

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 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 the computational and data efficiency of the brain.
In addition, autonomy and sociality are critical functions that are required for more versatile AI agents in the forthcoming human-AI society. We will discuss what we can learn from human society and human brain functions.

BIO

Kenji Doya is a Professor of Neural Computation Unit, Okinawa Institute of Science and Technology (OIST) Graduate University.
He took his PhD in 1991 at the University of Tokyo and worked as a postdoc at U. C. San Diego and the Salk Institute.
In 1994, he joined Advanced Telecommunications Research International (ATR) as a Senior Researcher and then served as a Group Leader of Kawato Dynamic Brain Project.
In 2004, he was appointed as a Principal Investigator of the OIST Initial Research Project and started Okinawa Computational Neuroscience Course (OCNC) as the chief organizer.
As OIST established itself as a Graduate University in 2011, he became a Professor and served as the Vice Provost for Research till 2014.
He is interested in reinforcement learning in both natural and artificial creatures.
He has served as a Co-Editor in Chief of Neural Networks from 2008 to 2021 and currently serves as a board member of International Neural Network Society (INNS) and the President of Japanese Neural Network Society (JNNS).
He serves as the Chairperson of Neuro2022 conference in Okinawa. He received INNS Donald O. Hebb Award in 2018, JNNS Academic Award, APNNS Outstanding Achievement Award, and the age-group 2nd place at Ironman Malaysia in 2022.
 

VIEW THE REPLAY