On the sample complexity of end-to-end training vs. semantic abstraction training
S Shalev-Shwartz, A Shashua - arXiv preprint arXiv:1604.06915, 2016 - arxiv.org
arXiv preprint arXiv:1604.06915, 2016•arxiv.org
We compare the end-to-end training approach to a modular approach in which a system is
decomposed into semantically meaningful components. We focus on the sample complexity
aspect, in the regime where an extremely high accuracy is necessary, as is the case in
autonomous driving applications. We demonstrate cases in which the number of training
examples required by the end-to-end approach is exponentially larger than the number of
examples required by the semantic abstraction approach.
decomposed into semantically meaningful components. We focus on the sample complexity
aspect, in the regime where an extremely high accuracy is necessary, as is the case in
autonomous driving applications. We demonstrate cases in which the number of training
examples required by the end-to-end approach is exponentially larger than the number of
examples required by the semantic abstraction approach.
We compare the end-to-end training approach to a modular approach in which a system is decomposed into semantically meaningful components. We focus on the sample complexity aspect, in the regime where an extremely high accuracy is necessary, as is the case in autonomous driving applications. We demonstrate cases in which the number of training examples required by the end-to-end approach is exponentially larger than the number of examples required by the semantic abstraction approach.
arxiv.org