Project Summary (Abstract)

The purpose of this project is to overcome the limitations of current neural network chips which generally have poor reconfigurability, and lack parameters for efficient learning. A new general-purpose analog neural network design is made for the TSMC 0.35um CMOS process. Parallel processing is possible with a massive array of independent cells, concurrently processing data. This allows the network to quickly recognize information in various applications. With support for multiple learning algorithms, arbitrary routing, high density, and storage of many parameters using improved high-resolution analog multi-valued memory, this network is suitable for vast improvements to the learning algorithms. Such improvements allow learning to interact with routing for a network which is not bound to a fixed layout. Other improvements include the interaction of multiple learning algorithms to learn partially by pattern, and partially by feedback.
Modified Backpropagation learning used with the learning rate parameters allows important data to be reinforced and retained, and insignificant data to be labile, providing improved learning speed. In addition to introducing the planned design for chip implementation, an op-amp prototype is created on a PC board. This prototype allows further development at cell-level, as well as a demonstration of the operation of the CMOS chip. SPICE is used for simulations of the CMOS circuit cells to determine accuracy and input/output range. Neuron circuits were found to be accurate, as was the Gilbert multiplier when input range was restricted. Neuron and synapse circuit design is complete, now in the simulation and layout phase.

VSF 2006 Project Information

Grade Grouping: 11
Team Size: 1
Subject Area: Engineering / Computer Science
Project Type: Descriptive
Project Format: Traditional

Software Tools

  • Website:
    • Macromedia Dreamweaver MX 2004
    • Macromedia Flash MX Professional 2004
    • SubEthaEdit 2.1
    • Panic Transmit 3.5
    • Apple Final Cut Pro HD 4.0
    • Adobe Photoshop CS
    • Adobe Acrobat 6 Professional
    • Microsoft Office X 2004
    • QuickTime 7 Pro
  • Project:
    • DJGPP C Compiler
    • Visual Basic 6.0
    • Access to Cadence Virtuoso for integrated circuit design, layout, and simulation
    • Cadence OrCad Capture for schematic design
    • Cadence OrCad Layout for printed circuit board design

Special Skills

  • Website:
    • HyperText Markup Language (HTML)
    • Cascading Style Sheets (CSS)
    • Macromedia Flash ActionScript
  • Project:
    • Knowledge of programming languages used
    • Circuit Design
    • Printed Circuit Board Layout
    • Soldering
    • Circuit Troubleshooting
    • Software Debugging
    • Microcontroller Programming
    • CMOS integrated circuit design
    • Algorithm Design and Testing
    • Love of Coffee :)

Hardware Tools

  • Website:
    • PowerBook G4 with Mac OS X 10.4.6
    • PC with Windows XP
    • PC with OpenSuSE Linux 10
  • Project:
    • PC with Windows 2000
    • MPLAB ICD 2 Microcontroller Debugger
    • 30MHz Oscilloscope
    • Multimeters
    • Logic Probe
    • 100MHz 18 Channel Logic Analyzer
    • Power Supply

Source of Idea

I have been interested in electronics for many years, and more recently also in neural networks. As part of my previous project, I proposed how a hardware neural network could be created with applications in robot vision and 3D object recognition. As my current project, I have done much research into previous hardware neural systems, and circuits which could be used in these systems, to create a fully reconfigurable hardware neural network design. Reconfigurability extends the hardware learning system concept into many applications.

Awards Received

  • Calgary Youth Science Fair (March 2006)
    • Gold Medal
    • University of Calgary Schulich School of Engineering First Place Award
    • Government of Alberta Travel Scholarship to Canada Wide Science Fair 2006
  • Intel International Science and Engineering Fair (Indianapolis, Indiana, May 2006)
    • Place on Team Canada awarded by Youth Science Foundation Canada
  • Canada Wide Science Fair (Saguenay, Quebec, May 2006)
    • Place on Team Calgary awarded by Calgary Youth Science Fair

Website: http://www.virtualsciencefair.org/2006/stag6m2 - posted on the Virtual Science Fair website at http://www.virtualsciencefair.com.
Copyright © Malcolm Stagg 2006. All Rights Reserved.
Website: http://www.virtualsciencefair.org/2006/stag6m2. Email: malcolmst@shaw.ca.