On a Fast, Compact Approximation of the Exponential Function

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.

Cite

Text

Cawley. "On a Fast, Compact Approximation of the Exponential Function." Neural Computation, 2000. doi:10.1162/089976600300015033

Markdown

[Cawley. "On a Fast, Compact Approximation of the Exponential Function." Neural Computation, 2000.](https://mlanthology.org/neco/2000/cawley2000neco-fast/) doi:10.1162/089976600300015033

BibTeX

@article{cawley2000neco-fast,
  title     = {{On a Fast, Compact Approximation of the Exponential Function}},
  author    = {Cawley, Gavin C.},
  journal   = {Neural Computation},
  year      = {2000},
  pages     = {2009-2012},
  doi       = {10.1162/089976600300015033},
  volume    = {12},
  url       = {https://mlanthology.org/neco/2000/cawley2000neco-fast/}
}