Showing 2016 · cs.NEShow all
2 papers · 2 filters
cs.NE2016
Dataflow matrix machines as programmable, dynamically expandable, self-referential generalized recurrent neural networks
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…
cs.NE2016
Dataflow Matrix Machines as a Generalization of Recurrent Neural Networks
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,…