Year: 2016
Type: preprint
Abstract: Dataflow matrix machines arise naturally in the context of synchronous dataflow programming with linear streams. They can be viewed as a rather powerful generalization of recurrent neural networks. Similarly to recurrent neural networks, large classes of dataflow matrix machines are described by matrices of numbers, and therefore dataflow matrix machines can be synthesized by computing their matrices. At the same time, the evidence is fairly strong that dataflow matrix machines have sufficient expressive power to be a convenient general-purpose programming platform. Because of the network nature of this platform, programming patterns often correspond to patterns of connectivity in the generalized recurrent neural networks understood as programs. This paper explores a variety of such programming patterns.
Source: arXiv (Cornell University)
Authors: Bukatin, Michael, Matthews, Steve, Radul, Andrey
Institution: University of Warwick
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2470528243