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.
Original language | English |
---|---|
Pages (from-to) | 2009-2012 |
Number of pages | 4 |
Journal | Neural Computation |
Volume | 12 |
Issue number | 9 |
DOIs | |
Publication status | Published - 2000 |