[SAIF 2019] Day 1: Towards Compositional Understanding of the World by Deep Learning - Yoshua Bengio

Humans are much better than current AI systems at generalizing out-of-distribution. What ingredients can bring us closer to that level of competence? We propose 4 ingredients combined: (a) meta-learning (to learn end-to-end to generalize to modified distributions, sampled from a distribution over distributions), (b) designing modular architectures with the property that modules are fairly independent of each other and interacting sparsely while made to be composed in new ways easily, (c) capturing causal st