A New Stochastic Computing Methodology for Efficient Neural Network Implementation
Authors:
- 23 April 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 27 (3) , 551-564
Abstract
This paper presents a new methodology for the hardware implementation of neural networks (NNs) based on probabilistic laws. The proposed encoding scheme circumvents the limitations of classical stochastic computing (based on unipolar or bipolar encoding) extending the representation range to any real number using the ratio of two bipolar-encoded pulsed signals. Furthermore, the novel approach presents practically a total noise-immunity capability due to its specific codification. We introduce different designs for building the fundamental blocks needed to implement NNs. The validity of the present approach is demonstrated through a regression and a pattern recognition task. The low cost of the methodology in terms of hardware, along with its capacity to implement complex mathematical functions (such as the hyperbolic tangent), allows its use for building highly reliable systems and parallel computing.Keywords
Funding Information
- Spanish Ministry of Economy and Competitiveness
- Regional European Development Funds
- Comunitat Autònoma de les Illes Balears (TEC2011-23113, TEC2014-56244-R, AAEE018/2012)
- European Social Fund through the Fellowship (FPI/1513/2012)
- Conselleria d’Educació, Cultura i Universitats through the Govern de les Illes Balears
This publication has 26 references indexed in Scilit:
- HARDWARE IMPLEMENTATION OF STOCHASTIC SPIKING NEURAL NETWORKSInternational Journal of Neural Systems, 2012
- Artificial neural network implementation on a single FPGA of a pipelined on-line backpropagation2005
- Evolution of fault-tolerant and noise-robust digital designsIEE Proceedings - Computers and Digital Techniques, 2004
- A digital architecture for support vector machines: theory, algorithm, and fpga implementationIEEE Transactions on Neural Networks, 2003
- Fully parallel summation in a new stochastic neural network architecture2002
- Stochastic neural computation. I. Computational elementsIEEE Transactions on Computers, 2001
- Fully parallel stochastic computation architectureIEEE Transactions on Signal Processing, 1996
- Functional abilities of a stochastic logic neural networkIEEE Transactions on Neural Networks, 1992
- VLSI implementation of synaptic weighting and summing in pulse coded neural-type cellsIEEE Transactions on Neural Networks, 1992
- A digital architecture employing stochasticism for the simulation of Hopfield neural netsIEEE Transactions on Circuits and Systems, 1989