assoc - retrieve associative memories
assoc [-pfile ...] [-tfile string] [-local integer]
[-cut double] [-pprob double] [-noise double]
[-seed integer] [-steps integer] [-inv] [-mag inte-
ger] [-term string]
Attempt to reconstruct a potentially corrupted image from
a McCulloch-Pitts feedback neural network that acts as an
associative memory. The weights of the network are deter-
mined via Hebb's rule after reading in multiple patterns.
Weights can be pruned either by size, locality, or ran-
File with pattern to store.
File with test pattern.
locality of permitted weights
Cutoff size for weights.
Probability of random pruning.
Amount of noise for test case.
Random seed for initial state.
Number of time steps.
-inv Invert all colors?
How to plot points.
All pattern files must be in the PBM file format. You can
request that multiple patterns be stored into the weights
by using the -pfile option multiple time.
The dimensions of the stored patterns and the test pattern
must be identical.
For weight pruning, the program first checks to see if a
weight is "non-local" which means that for a weight that
connects two neurons either the row indices or column
indices differ by the amount greater than the value speci-
fied by the -local option. (If a value for local -local
is zero, then all weights are used.) Next, the program
prunes weights that are too small in size as specified by
the -cut option. If a weights has not been removed at
this stage, then it will still be pruned with probability
as specified by the -pprob option.
No sanity checks are performed to make sure that any of
the options make sense.
Copyright (c) 1997, Gary William Flake.
Permission granted for any use according to the standard
GNU ``copyleft'' agreement provided that the author's com-
ments are neither modified nor removed. No warranty is
given or implied.
Man(1) output converted with