1 code implementation • 3 Jul 2019 • Sam Wenke, Dan Saunders, Mike Qiu, Jim Fleming
We instead propose transfers that produce multiple test sets that are used to measure specified types of generalization, inspired by abilities demonstrated by animal and human tool users.
1 code implementation • 9 Feb 2019 • Sam Wenke, Jim Fleming
There is an implicit assumption that by unfolding recurrent neural networks (RNN) in finite time, the misspecification of choosing a zero value for the initial hidden state is mitigated by later time steps.