it has been suggested to me that the following technical note (available
by anonymous ftp) may be of particular interest to the neural modelling
community. My apologies to those who have already seen it announced
on the connectionists mailing list.
Best regards,
--
Dr. Nicol N. Schraudolph Tel: +41-91-970-3877
IDSIA Fax: +41-91-911-9839
Corso Elvezia 36
CH-6900 Lugano http://www.idsia.ch/~nic/
Switzerland http://www.cnl.salk.edu/~schraudo/
Technical Report IDSIA-07-98:
A Fast, Compact Approximation of the Exponential Function
---------------------------------------------------------
Nicol N. Schraudolph
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
note 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.