Linear Models of Computation and Program Learning

13 pages•Published: December 18, 2015

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.

Keyphrases: bilattices, bitopology, extended interval numbers, fuzzy sampling, generalized animation, negative probability, probabilistic programming

In: Georg Gottlob, Geoff Sutcliffe and Andrei Voronkov (editors). GCAI 2015. Global Conference on Artificial Intelligence, vol 36, pages 66-78.

Links:	https://easychair.org/publications/paper/Q4lW
	https://doi.org/10.29007/rbdd

BibTeX entry

@inproceedings{GCAI2015:Linear_Models_Computation_Program,
  author    = {Michael Bukatin and Steve Matthews},
  title     = {Linear Models of Computation and Program Learning},
  booktitle = {GCAI 2015. Global Conference on Artificial Intelligence},
  editor    = {Georg Gottlob and Geoff Sutcliffe and Andrei Voronkov},
  series    = {EPiC Series in Computing},
  volume    = {36},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/Q4lW},
  doi       = {10.29007/rbdd},
  pages     = {66-78},
  year      = {2015}}

Download PDF Open PDF in browser