Next: Mean Field Annealing
Up: The Hopfield Net
Previous: Stability of the
We believe that this is probably the most important phase when dealing
with computational models such as neural nets. Suppose we are given an
optimization problem then we need to consider the following steps:
- A representation of the problem is needed in which the feasible
solutions lie at hypercube
vertices.
- Each hypercube vertex is regarded as a configuration of the
problem, with an associated energy (or cost) function.
- The partition function is then formed by summing the Boltzmann
factors of the admissible configurations.
- A quadratic energy function (to be mapped onto the first term of
equation (9)) for which the minima correspond to solutions
and the depth of each minimum reflects the solution quality.
Hopfield and Tank mapped the TSP onto their model using a permutation
matrix representation of the TSP tours. Other likewise problems can be
mapped using a similar representation.
HPF demo web account
Mon Nov 18 19:45:42 EST 1996