C++ Neural Networks and Fuzzy Logic: Preface

Hidden Layer Neuron#Weighted SumCommentActivationContribution to OutputSum

O :0, 0, 010<1.800

20<0.0500

30>−0.210.60.6

*

A :0, 0, 110.2<1.800

20.3>0.0510.3

30.6>−0.210.60.9

*

B :0, 1, 011<1.800

2−1<0.0500

3−1<−0.2000

C :0, 1, 111.2<1.800

20.2>0.0510.3

3−0.4<−0.2000.3

D :1, 0, 011<1.800

2.1>0.0510.3

3−1<−0.2000.3

E :1, 0, 111.2<1.800

20.4>0.0510.3

3−0.4<−0.2000.3

F :1, 1, 012>1.810.6

C++ Neural Networks and Fuzzy Logic:Preface

Performance of the Perceptron

88

---

2−0.9<0.0500

3−2<−0.2000.6

*

*

The output neuron fires, as this value is greater than 0.5 (the threshold value); the function value is +1.

Other Two−layer Networks

Many important neural network models have two layers. The Feedforward backpropagation network, in its

simplest form, is one example. Grossberg and Carpenter’s ART1 paradigm uses a two−layer network. The

Counterpropagation network has a Kohonen layer followed by a Grossberg layer. Bidirectional Associative

Memory, (BAM), Boltzman Machine, Fuzzy Associative Memory, and Temporal Associative Memory are

other two−layer networks. For autoassociation, a single−layer network could do the job, but for

heteroassociation or other such mappings, you need at least a two−layer network. We will give more details

on these models shortly.