Linear Models of Computation and Program Learning
Logic in Computer Science
2015-12-17 v1 Neural and Evolutionary Computing
Abstract
We consider two classes of computations which admit taking linear combinations of execution runs: probabilistic sampling and generalized animation. We argue that the task of program learning should be more tractable for these architectures than for conventional deterministic programs. We look at the recent advances in the "sampling the samplers" paradigm in higher-order probabilistic programming. We also discuss connections between partial inconsistency, non-monotonic inference, and vector semantics.
Cite
@article{arxiv.1512.04639,
title = {Linear Models of Computation and Program Learning},
author = {Michael Bukatin and Steve Matthews},
journal= {arXiv preprint arXiv:1512.04639},
year = {2015}
}
Comments
13 pages; September 3, 2015 version; to appear in the Proceedings of GCAI 2015, Tbilisi, Georgia, Oct.16-18, 2015