Using PHiPAC to speed error back-propagation learning

Jeff A. Bilmes, Krste Asanovic, Chee-Whye Chin, James Demmel

Abstract

We introduce PHiPAC, a coding methodology for developing portable high-performance numerical libraries in ANSI C. Using this methodology, we have developed code for optimized matrix multiply routines. These routines can achieve over 90% of peak performance on a variety of current workstations, and are often faster than vendor-supplied optimized libraries. We then describe the bunch-mode back-propagation algorithm and how it can use the PHiPAC derived matrix multiply routines. Using a set of plots, we investigate the tradeoffs between bunch size, convergence rate, and training speed using a standard speech recognition data set and show how use of the PHiPAC routines can lead to a significantly faster back-propagation learning algorithm.
BibTeX
@inproceedings{bilmes1997using,
  author = {Jeff A. Bilmes and Krste Asanovic and Chee-Whye Chin and James Demmel},
  title = {{Using PHiPAC to speed error back-propagation learning}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {1997},
  doi = {10.1109/icassp.1997.604861},
}

Loading related content...

Figure