Index Terms
- First specialize, then generalize: introduction
Recommendations
Sharp minima can generalize for deep nets
ICML'17: Proceedings of the 34th International Conference on Machine Learning - Volume 70Despite their overwhelming capacity to overfit, deep learning architectures tend to generalize relatively well to unseen data, allowing them to be deployed in practice. However, explaining why this is the case is still an open area of research. One ...
Learning to Generalize from Demonstrations
AbstractLearning by demonstration is a natural approach that can be used to build a robot’s task repertoire. In this paper we propose an algorithm that enables a learner to generalize a task representation from a small number of demonstrations of ...
Policies that generalize: solving many planning problems with the same policy
IJCAI'15: Proceedings of the 24th International Conference on Artificial IntelligenceWe establish conditions under which memoryless policies and finite-state controllers that solve one partially observable non-deterministic problem (PONDP) generalize to other problems; namely, problems that have a similar structure and share the same ...
Comments