C++ Neural Networks and Fuzzy Logic: Preface

Network Modeling

So far, we have considered the construction of two networks, the Hopfield memory and the Perceptron. What

are other considerations (which will be discussed in more depth in the chapters to follow) that you should

keep in mind ?

Some of the considerations that go into the modeling of a neural network for an application are:

nature of inputs

       fuzzy

                 binary

                 analog

       crisp

                 binary

                 analog

number of inputs

nature of outputs

       fuzzy

                 binary

                 analog

       crisp

                 binary

                 analog

C++ Neural Networks and Fuzzy Logic:Preface

Network Modeling

72

---

number of outputs

nature of the application

       to complete patterns (recognize corrupted patterns)

       to classify patterns

       to do an optimization

       to do approximation

       to perform data clustering

       to compute functions

dynamics

adaptive

learning

training

                                           with exemplars

                                           without exemplars