Two properties of some binary input vector are the truth values of the following expressions:
1) There are more `ones' on the `right' side of the input vector than on the `left' side.
2) The input vector consists of more `ones' than `zeros'.
During one learning cycle,
a randomly chosen legal input vector was presented to
, another input vector
randomly chosen among those with the feature combination
of the first one
was presented to
.
and were constrained to have the same weights.
Input vectors with equal numbers of ones and zeros as well as
input vectors with equal numbers of ones on both sides
were excluded.
We minimized (4) with
defined by an auto-encoder (equation (7)).
Ten test runs involving 15,000 pattern presentations
were conducted. The system always came up with a distributed near-binary
representation of the possible feature combinations.
With defined by modified
predictability minimization (equation (9)),
with simultaneous training of both predictors and classifiers,
ten test runs
involving 10,000 pattern presentations
were conducted.
Again, the system always learned to extract the two features.