[Cover] [Contents] [Index] |
Page 123
Figure 3.10 Counter-propagation network acts as an associated memory. See text for details.
(3.18) |
where:
(3.19) |
When an input vector is fed into the network, the following weighted sum is calculated for each hidden neurone j:
(3.20) |
The winning neurone v in the hidden layer is that which has the
[Cover] [Contents] [Index] |