Abstract:
Efficient hardware implementations of neural networks are of high interest. Stochastic computing is an alternative to conventional digital logic that allows to exploit th...Show MoreMetadata
Abstract:
Efficient hardware implementations of neural networks are of high interest. Stochastic computing is an alternative to conventional digital logic that allows to exploit the intrinsic parallelism of neural networks using few hardware resources. We present a new stochastic methodology that extends the capabilities of classical stochastic computing. In particular, the present approach exhibits practically total immunity to noise. This is demonstrated evaluating the influence of the noise on the system's performance for a mathematical regression task.
Date of Conference: 12-17 July 2015
Date Added to IEEE Xplore: 01 October 2015
ISBN Information: