Discrete and Stochastic Aspect of Cognitively Inspired Machine Learning 

[CFAR Rising Star Lecture Series]
Discrete and Stochastic Aspect of Cognitively Inspired Machine Learning by Dr Liu Dianbo
31 Oct 2022 | 9.30am (Singapore Time)

Deep learning has advanced from fully connected architectures to structured models organised into components, e.g., the transformer composed of positional elements, modular architectures divided into slots, and graph neural nets made up of nodes. Inspired by the human brain, components in such models face communication bottlenecks due to restricted connectivity and attention, which may serve as a useful form of inductive bias. In addition, human consciousness works in a stochastic manner, in which different neurons and sub-structures are activated differently upon different internal and external stimuli.

In this talk, Dr Liu Dianbo from Mila - Quebec Artificial Intelligence (AI) Institute will illustrate how the bottleneck of communication among modules and input-dependent stochastic activation could help in out-of-distribution generalisation and uncertainty estimation of the deep learning models.


SPEAKER
talks---liu dian bo
Dr Liu Dianbo 
Postdoctoral Researcher
Leader of Humanitarian AI team
Mila - Quebec AI Institute



Dr Liu Dianbo is a postdoctoral machine learning researcher in Prof Yoshua Bengio (Turing Award 2018) group, Mila-Quebec AI institute. Dr Liu's research on AI focuses on consciousness inspired machine learning for artificial general intelligence (AGI). He is also leading the humanitarian AI team of 19 researchers at Mila, which includes research on both fundamental machine learning and its applications in improving the quality of human in the medical aspect. Prior to joining the Bengio team, he worked and studied at University of Dundee, Harvard University and Massachusetts Institute of Technology. Dr Liu co-found and served as the first CTO of Secure AI Labs, MA, USA, a MIT spin-off that focuses on machine learning for social good. In his personal life, Dr Liu is a stand-up comedian in training and has travelled across most continents in the world.