Web-enabled neuron model hardware implementation and testing

Fearghal Morgan, Finn Krewer, Frank Callaly, Aedan Coffey, Brian McGinley

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

3 Citations (Scopus)

Abstract

This paper presents a prototype web-based Graphical User Interface (GUI) platform for integrating and testing a system that can perform Low-Entropy Model Specification (LEMS) neural network description to Hardware Description Language (VHDL) conversion, and automatic synthesis and neuron implementation and testing on Field Programmable Gate Array (FPGA) testbed hardware. This system enables hardware implementation of neuron components and their connection in a small neural network testbed. This system incorporates functionality for automatic LEMS to synthesisable VHDL translation, automatic VHDL integration with FPGA logic to enable data I/O, automatic FPGA bitfile generation using Xilinx PlanAhead, automated multi- FPGA testbed configuration, neural network parameter configuration and flexible testing of FPGA based neuron models. The prototype UI supports clock step control and real-time monitoring of internal signals. References are provided to video demonstrations.

Original languageEnglish
Title of host publicationNEUROTECHNIX 2015 - Proceedings of the 3rd International Congress on Neurotechnology, Electronics and Informatics
EditorsAldo Faisal, Hermano Igo Krebs, Antonio Pedotti
PublisherSCITEPRESS
Pages138-145
Number of pages8
ISBN (Electronic)9789897581618
DOIs
Publication statusPublished - 2015
Event3rd International Congress on Neurotechnology, Electronics and Informatics, NEUROTECHNIX 2015 - Lisbon, Portugal
Duration: 16 Nov 201517 Nov 2015

Publication series

NameNEUROTECHNIX 2015 - Proceedings of the 3rd International Congress on Neurotechnology, Electronics and Informatics

Conference

Conference3rd International Congress on Neurotechnology, Electronics and Informatics, NEUROTECHNIX 2015
Country/TerritoryPortugal
CityLisbon
Period16/11/1517/11/15

Keywords

  • Biological neural networks
  • Brain-inspired computation
  • FPGA hardware neural networks
  • Low entropy model specification (LEMS)
  • VHDL
  • Web-enabled neural capture

Fingerprint

Dive into the research topics of 'Web-enabled neuron model hardware implementation and testing'. Together they form a unique fingerprint.

Cite this