Dataflow Matrix Machines as a Model of Computations with Linear Streams
Neural and Evolutionary Computing
2017-06-05 v1 Machine Learning
Programming Languages
Abstract
We overview dataflow matrix machines as a Turing complete generalization of recurrent neural networks and as a programming platform. We describe vector space of finite prefix trees with numerical leaves which allows us to combine expressive power of dataflow matrix machines with simplicity of traditional recurrent neural networks.
Cite
@article{arxiv.1706.00648,
title = {Dataflow Matrix Machines as a Model of Computations with Linear Streams},
author = {Michael Bukatin and Jon Anthony},
journal= {arXiv preprint arXiv:1706.00648},
year = {2017}
}
Comments
6 pages, accepted for presentation at LearnAut 2017: Learning and Automata workshop at LICS (Logic in Computer Science) 2017 conference. Preprint original version: April 9, 2017; minor correction: May 1, 2017