Basic HTML version of Foils prepared 15 March 1996

Foil 70 Neural Networks for Track Finding

From Physical Optimization and Physical Computation CPSP713 Case studies in Computational Science -- Spring Semester 1996. by Geoffrey C. Fox
1 Analogy to Travelling Salesperson Problem:
  • Hopfield-Tank use h(x) with x = (x,t) with t labelling tour and x labelling city
  • Two critical differences
    • TSP: Only 1 tour so Hopfield-Tank very redundant and must satisfy difficult constraint
    • Vision: Many tours and indeed unknown number of tours, so less redundancy and no constraints!
2 TRW have implemented this approach to tracking
3 Neural network degrees of freedom independent of number of tracks! (Kalman filter gets difficult as number of tracks becomes large and unknown)
4 Neural network has essentially unlimited parallelism
5 Again neural networks "work" when these are natural degrees of freedom
in Table To:

Northeast Parallel Architectures Center, Syracuse University, npac@npac.syr.edu

If you have any comments about this server, send e-mail to webmaster@npac.syr.edu.

Page produced by wwwfoil on Sun Feb 22 1998