Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Probabilistic Neural Programs
Kenton Murray, Jayant Krishnamurthy
Oct 14, 2016 (modified: Oct 14, 2016)NIPS 2016 workshop NAMPI submissionreaders: everyone
Abstract:We present probabilistic neural programs, a framework for program induction that permits flexible specification of both a computational model and inference algorithm while simultaneously enabling the use of deep neural networks. Probabilistic neural programs combine a computation graph for specifying a neural network with an operator for weighted nondeterministic choice. Thus, a program describes both a collection of decisions as well as the neural network architecture used to make each one. We evaluate our approach on a challenging diagram question answering task where probabilistic neural programs correctly execute nearly twice as many programs as a baseline model.
TL;DR:We present probabilistic neural programs, a framework for program induction using neural nets and probabilistic programming.
Conflicts:nd.ed, allenai.org, cmu.edu
Enter your feedback below and we'll get back to you as soon as possible.