A Fast, Compact Approximation of the Exponential Function

Neural network simulations often spend a large proportion of their time computing exponential functions. Since the exponentiation routines of typical math libraries are rather slow, their replacement with a fast approximation can greatly reduce the overall computation time. This article describes ho...

Full description

Saved in:
Bibliographic Details
Published in:Neural computation 1999-05, Vol.11 (4), p.853-862
Main Author: Schraudolph, Nicol N.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial intelligence
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Logistic Models
Mathematics
Methods of scientific computing (including symbolic computation, algebraic computation)
Neural Networks (Computer)
Nonlinear Dynamics
Numerical analysis
Numerical analysis. Scientific computation
Numerical approximation
Reproducibility of Results
Sciences and techniques of general use
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural network simulations often spend a large proportion of their time computing exponential functions. Since the exponentiation routines of typical math libraries are rather slow, their replacement with a fast approximation can greatly reduce the overall computation time. This article describes how exponentiation can be approximated by manipulating the components of a standard (IEEE-754) floating-point representation. This models the exponential function as well as a lookup table with linear interpolation, but is significantly faster and more compact.
ISSN:0899-7667
1530-888X
DOI:10.1162/089976699300016467