Parallelization of algorithms with recurrent neural networks

Authors:
João Pedro Neto;Fernando Silva
Affiliations:
Dept. Informatics, Faculty of Sciences, University of Lisbon, Portugal;Dept. Informatics, Faculty of Sciences, University of Lisbon, Portugal
Venue:
ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part I
Year:
2011

Citing 5
Cited 0

Analog computation via neural networks

Theoretical Computer Science
A neural compiler

Theoretical Computer Science
Neural networks and analog computation: beyond the Turing limit

Neural networks and analog computation: beyond the Turing limit
Parallel computation in spiking neural nets

Theoretical Computer Science
A virtual machine for neural computers

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural networks can be used to describe symbolic algorithms like those specified in high-level programming languages. This article shows how to translate these network description of algorithms into a more suitable format in order to feed an arbitrary number of parallel processors to speed-up the computation of sequential and parallel algorithms.