A Fast, Compact Approximation of the Exponential Function (1998) [13 citations — 4 self]
Download:
ftp://ftp.idsia.ch/pub/techrep/IDSIA-07-98.ps.gz
ftp://ftp.idsia.ch/pub/nic/exp.ps.gz
http://www.inf.ethz.ch/~schraudo/pubs/exp.ps.gz
DBLP
CACHED:
|
ftp://ftp.idsia.ch/pub/techrep/IDSIA-07-98.ps.gz
ftp://ftp.idsia.ch/pub/nic/exp.ps.gz
http://www.inf.ethz.ch/~schraudo/pubs/exp.ps.gz
DBLP
CACHED:
|
by
Nicol N. Schraudolph
Neural Computation
Add To MetaCart
Popular Tags
No tags have been applied to this document.
BibTeX | Add To MetaCart
@ARTICLE{Schraudolph98afast,,
author = {Nicol N. Schraudolph},
title = {A Fast, Compact Approximation of the Exponential Function},
journal = {Neural Computation},
year = {1998},
volume = {11},
pages = {11--4}
}
author = {Nicol N. Schraudolph},
title = {A Fast, Compact Approximation of the Exponential Function},
journal = {Neural Computation},
year = {1998},
volume = {11},
pages = {11--4}
}
Bookmarks
OpenURL
Abstract:
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 paper 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.
Citations
| 65 | Standard for Binary Floating-Point Arithmetic. ANSI/IEEE Standard 754-1985. Available from http://www.ieee.org – IEEE |
| 50 | On the Lambert W Function – Corless, Gonnet, et al. - 1996 |
| 8 | Algorithm 443: Solution of the transcendental equation w e w = x – Fritsch, Shafer, et al. - 1973 |
| 6 | standard for binary oating-point arithmetic – IEEE - 1985 |
| 1 | JPEG quality transcoding using neural networks trained with a perceptual error measure – unknown authors - 1999 |
