Human-Inspired Inductive Biases for Causal Reasoning and Out-of-Distribution Generalization
, University of Montreal, Mila - Quebec Artificial Intelligence Institute
Humans are very good at out-of-distribution generalization (at least compared to current AI systems), and it would be good to understand some of the inductive biases we exploit and test these theories by evaluating how they can be translated into successful ML architectures, training frameworks, and experiments. Natural language and experimental results in cognitive science and neuroscience provide a wealth of clues about the system 2 part of how humans understand the world and reason about it. I'll discuss several of these hypothesized inductive biases, many of which exploit notions in causality and connect the discovery of abstractions in representation learning (the perception and interpretation part) and in reinforcement learning (the abstract actions). Systematic generalization is hypothesized to arise from an efficient factorization of knowledge into recomposable pieces corresponding to reusable factors (in a directed factor graph formulation). This is related to, yet different in many ways from, symbolic AI (and this can be seen in the errors and limitations of reasoning in humans, as well as in our ability to learn to do this at scale, with distributed representations and efficient search). Sparsity of the causal graph and locality of interventions — which can be observed in the structure of sentences — could considerably reduce the computational complexity of both inference (including planning) and learning, which may be why evolution incorporated this "consciousness." Although this talk will rest on a series of recent papers on these topics (i.e., on learning causal and/or modular structure with deep learning), much of it will be forward-facing and suggest open research questions in the hope of stimulating novel investigations and collaborations. A recent review of many of these points can be found in https://arxiv.org/abs/2011.15091