• Computer Science
  • Published in ArXiv 2016

Probabilistic Neural Programs

@article{Murray2016ProbabilisticNP,
  title={Probabilistic Neural Programs},
  author={Kenton W. Murray and Jayant Krishnamurthy},
  journal={ArXiv},
  year={2016},
  volume={abs/1612.00712}
}
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… CONTINUE READING
11
Twitter Mentions

Citations

Publications citing this paper.
SHOWING 1-4 OF 4 CITATIONS

Program Synthesis from Visual Specification

VIEW 1 EXCERPT
CITES BACKGROUND

Structured Set Matching Networks for One-Shot Part Labeling

VIEW 2 EXCERPTS
CITES METHODS

Visual Question Answering: A Tutorial

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 13 REFERENCES

Neural Turing Machines

VIEW 1 EXCERPT