C++ Neural Networks and Fuzzy Logic: Preface

Figure 5.1a

  Example network.

Table 5.2 Results for the Perceptron with One Hidden Layer.

InputHidden Layer ActivationsHidden Layer OutputsOutput Neuron activatonOutput of network

(0, 0)(0, 0)(0, 0)00

(1, 1)(0.3, 0.6)(1, 1)00

(0, 1)(0.15, 0.3)(0, 1)0.31

(1, 0)(0.15, 0.3)(0, 1)0.31

It is clear from Table 5.2, that the above perceptron with a hidden layer does compute the XOR function

successfully.

Note:  The activation should exceed the threshold value for a neuron to fire. Where the

output of a neuron is shown to be 0, it is because the internal activation of that neuron fell

short of its threshold value.

C++ Neural Networks and Fuzzy Logic:Preface

A Second Look at the XOR Function: Multilayer Perceptron

84

---