Dataflow matrix machines as programmable, dynamically expandable, self-referential generalized recurrent neural networks

2016-05-17 · Michael Bukatin, Steve Matthews, Andrey Radul

Dataflow matrix machines are a powerful generalization of recurrent neural networks. They work with multiple types of linear streams and multiple types of neurons, including higher-order neurons which dynamically update the matrix describing weights and topology of the network in question while the network is running. It seems that the power of dataflow matrix machines is sufficient for them to be a convenient general purpose programming platform. This paper explores a number of useful programming idioms and constructions arising in this context.

📄 PDF Abstract BibTeX arXiv:1605.05296

Code (1)

anhinga/fluid

Programming Patterns in Dataflow Matrix Machines and Generalized Recurrent Neural Nets

2016-06-30 · Michael Bukatin, Steve Matthews, Andrey Radul

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…

Dataflow Matrix Machines as a Model of Computations with Linear Streams

2017-05-03 · Michael Bukatin, Jon Anthony

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 t…

Dataflow Matrix Machines and V-values: a Bridge between Programs and Neural Nets

2017-12-20 · Michael Bukatin, Jon Anthony

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…

Dataflow Matrix Machines as a Generalization of Recurrent Neural Networks

2016-03-29 · Michael Bukatin, Steve Matthews, Andrey Radul

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 co…

BIG-bench Machine Learning Probabilistic Programming

Dynamically Reconfigurable Variable-precision Sparse-Dense Matrix Acceleration in Tensorflow Lite

2023-04-17 · Jose Nunez-Yanez, Andres Otero, Eduardo de la Torre

In this paper, we present a dynamically reconfigurable hardware accelerator called FADES (Fused Architecture for DEnse and Sparse matrices). The FADES design offers multiple configuration options that trade off paralleli…