Year: 2017
Type: preprint
Abstract: 1) Dataflow matrix machines (DMMs) generalize neural nets by replacing streams of numbers with linear streams (streams supporting linear combinations), allowing arbitrary input and output arities for activation functions, countable-sized networks with finite dynamically changeable active part capable of unbounded growth, and a very expressive self-referential mechanism. 2) DMMs are suitable for general-purpose programming, while retaining the key property of recurrent neural networks: programs are expressed via matrices of real numbers, and continuous changes to those matrices produce arbitrarily small variations in the associated programs. 3) Spaces of V-values (vector-like elements based on nested maps) are particularly useful, enabling DMMs with variadic activation functions and conveniently representing conventional data structures.
Source: arXiv (Cornell University)
Authors: Bukatin, Michael, Anthony, Jon
Institution: Boston College
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2776725332