
✐
✐
“4137X˙CH05˙Akerkar” — 2007/9/8 — 11:01 — page 191 — #15
✐
✐
✐
✐
✐
✐
5.3 Neural-Network-Based Approaches 191
and apply the activation function to v. Thus, the computation of each input pattern will be
given as
P
1
: v =2× 1 − 4 × 0+1× 0=2,
2 > 0,y = ϕ(2) = 1.
P
2
: v =2× 0 − 4 × 1+1× 1=−3,
− 3 < 0,y = ϕ(−3) = 0.
P
3
: v =2× 1 − 4 × 0+1× 1=3,
3 > 0,y = ϕ(3) = 1.
P
4
: v =2× 1 − 4 × 1+1× 1=−1,
− 1 < 0,y = ϕ(−1) = 0.
Here, the training set is a set of pairs of input patterns with corresponding desired-output
patterns. Each pair represents how the network is supposed to respond to a particular input.
The network is trained to respond correctly to each input pattern from ...