Programming Patterns in Dataflow Matrix Machines and Generalized Recurrent Neural Nets
This work is incremental, proposing a programming platform for AI/ML applications without demonstrating new performance gains.
The paper explores programming patterns in dataflow matrix machines, which generalize recurrent neural networks, by linking these patterns to connectivity structures in networks, but does not report specific results or numbers.
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.