Neural networks
Download as PPTX, PDF1 like661 views
This document discusses neural networks and their components. It defines a neural network as a directed graph with input, hidden, and output nodes partitioned into layers. Nodes are connected by weighted arcs and labeled with activation functions. Neural networks learn by propagating input values through the graph, comparing outputs to targets, and adjusting weights. Their advantages include learning ability, parallelization, and solving complex problems, while disadvantages are difficulty understanding them and overfitting. Applications include prediction, classification, data processing, and filtering.
![NN Activation Functions
6
Functions associated with nodes in graph.
Output may be in range [-1,1] or [0,1]
© Prentice Hall](https://image.slidesharecdn.com/neuralnetworks-121019003044-phpapp02/85/Neural-networks-6-320.jpg)
Neural networks
- 1. DATA WARE HOUSING AND DATA MINING NEURAL NETWORKS
- 2. Contents Neural Networks NN Node NN Activation Functions NN Learning NN Advantages NN Disadvantages
- 3. Neural Networks 3 Based on observed functioning of human brain. (Artificial Neural Networks (ANN) Our view of neural networks is very simplistic. We view a neural network (NN) from a graphical viewpoint. Alternatively, a NN may be viewed from the perspective of matrices. Used in pattern recognition, speech recognition, computer vision, and classification. © Prentice Hall
- 4. Neural Networks 4 Neural Network (NN) is a directed graph F=<V,A> with vertices V={1,2,…,n} and arcs A={<i,j>|1<=i,j<=n}, with the following restrictions: V is partitioned into a set of input nodes, VI, hidden nodes, VH, and output nodes, VO. The vertices are also partitioned into layers Any arc <i,j> must have node i in layer h-1 and node j in layer h. Arc <i,j> is labeled with a numeric value wij. Node i is labeled with a function fi. © Prentice Hall
- 5. Neural Network Example 5 © Prentice Hall
- 6. NN Activation Functions 6 Functions associated with nodes in graph. Output may be in range [-1,1] or [0,1] © Prentice Hall
- 7. NN Activation Functions 7 © Prentice Hall
- 8. NN Learning 8 Propagate input values through graph. Compare output to desired output. Adjust weights in graph accordingly. © Prentice Hall
- 9. Neural Networks 9 A Neural Network Model is a computational model consisting of three parts: Neural Network graph Learning algorithm that indicates how learning takes place. Recall techniques that determine hew information is obtained from the network. We will look at propagation as the recall technique. © Prentice Hall
- 10. NN Advantages 10 Learning Can continue learning even after training set has been applied. Easy parallelization Solves many problems © Prentice Hall
- 11. NN Disadvantages 11 Difficult to understand May suffer from overfitting Structure of graph must be determined a priori. Input values must be numeric. Verification difficult. © Prentice Hall
- 12. Applications of Neural 12 Networks Prediction – weather, stocks, disease Classification – financial risk assessment, image processing Data association – Text Recognition (OCR) Data conceptualization – Customer purchasing habits Filtering – Normalizing telephone signals (static)