Dataflow Matrix Machines as a Generalization of Recurrent Neural Networks

Abstract

Dataflow matrix machines are a powerful generalization of recurrent neural networks. They work with multiple types of arbitrary linear streams, multiple types of powerful neurons, and allow to incorporate higher-order constructions. We expect them to be useful in machine learning and probabilistic programming, and in the synthesis of dynamic systems and of deterministic and probabilistic programs.

4 pages position paper (v2 - update references)