Gang Fang's Blog

In Yoshua’s blog post introducing the GFlowNets, most concepts used to describe the new framework are something I don’t know.

So, the first phase is to understand all basic concepts:

• System 2 inductive biases
• reinforcement learning, deep generative models and energy-based probabilistic modelling
• non-parametric Bayesian modelling, generative active learning, and unsupervised or self-supervised learning of abstract representations
• explanatory causal factors
• out-of-distribution generalization
• free energies