An efficient implementation of a backpropagation learning algorithm on a Quadrics parallel supercomputer

Sergio Taraglio, Federico Massaioli

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

A parallel implementation of a library to build and train Multi Layer Perceptions via the Back Propagation algorithm is presented. The target machine is the SIMD massively parallel supercomputer Quadrics. Performance measures are provided on three different machines with different number of processors, for two network examples. A sample source code is given.
Original languageEnglish
DOIs
Publication statusPublished - 1995
EventInternational Conference and Exhibition on High-Performance Computing and Networking, HPCN Europe 1995 - Milan, Italy
Duration: 1 Jan 1995 → …

Conference

ConferenceInternational Conference and Exhibition on High-Performance Computing and Networking, HPCN Europe 1995
CountryItaly
CityMilan
Period1/1/95 → …

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

Taraglio, S., & Massaioli, F. (1995). An efficient implementation of a backpropagation learning algorithm on a Quadrics parallel supercomputer. Paper presented at International Conference and Exhibition on High-Performance Computing and Networking, HPCN Europe 1995, Milan, Italy. https://doi.org/10.1007/BFb0046696_97