Communications of the ACM
Yoshua Bengio: 'I Have Rarely Been as Enthusiastic about a New Research Direction'
Credit: Camille Gladu-Drouin
Recognized worldwide as one of the leading experts in AI, Yoshua Bengio is a full professor at Université de Montréal, founder and scientific director of Mila—Quebec AI Institute, and 2018 A.M. Turing Award recipient.
Generative Flow Networks, or GFlowNets, "live somewhere at the intersection of reinforcement learning, deep generative models and energy-based probabilistic modelling," writes Bengio in one of his latest blog posts. Related to variational models and inference, he believes GFlowNets open new doors for non-parametric Bayesian modeling, generative active learning, and unsupervised or self-supervised learning of abstract representations to disentangle both the explanatory causal factors and the mechanisms that relate them.
"The appropriate optimization algorithms are still making rapid progress, and many opportunities probably waiting for us in upcoming research."
From YoshuaBengio.com
View Full Article
No entries found