SAIF 2019 Day 1: Adapting and Explaining Deep Learning for Autonomous Systems Trevor Darrell

Learning of layered or deep representations has recently enabled lowcost sensors for autonomous vehicles and efficient automated analysis of visual semantics in online media. But these models have typically required prohibitive amounts of training data, and thus may only work well in the environment they have been trained in. Ill describe recent methods in adversarial adaptive learning that excel when learning across modalities and domains. Further, these models have been unsatisfying in their complexit