On a Fast, Compact Approximation of the Exponential Function

Authors:
Gavin C. Cawley
Affiliations:
University of East Anglia, Norwich, Norfolk NR4 7TJ, England
Venue:
Neural Computation
Year:
2000

Citing 2
Cited 2

JPEG quality transcoding using neural networks trained with a perceptual error measure

Neural Computation
A fast, compact approximation of the exponential function

Neural Computation

Multistep-ahead neural-network predictors for network traffic reduction in distributed interactive applications

ACM Transactions on Modeling and Computer Simulation (TOMACS)
A fast, streaming simd extensions 2, logistic squashing function

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently Schraudolph (1999) described an ingenious, fast, and compact approximation of the exponential function through manipulation of the components of a standard (IEEE-754 (IEEE, 1985)) floating-point representation. This brief note communicates a recoding of this procedure that overcomes some of the limitations of the original macro at little or no additional computational expense.