1.NEURAL NETWORKSM.H.Vinay Charan08P71A12C0

2. What is a Neural Network?An artificial neural network (ANN), often just called a "neural network" (NN), is a mathematical model or computational model based on biological ` neural networks, in other words, is an emulation of biological neural system. 3. Data MiningData mining is the term used to describe the process of extracting value from a database. Four things are required to data-mine effectively: ` High-quality data. right data. Adequate sample size. Right tool. 4. Why Neural Network? Neural networks are useful for data mining and decision-support applications. People are good at generalizing from experience.` Computers excel at following explicit instructions over andover. Neural networks bridge this gap by modeling, on acomputer, the neural behavior of human brains. 5. ANN Characteristics Neural networks are useful for pattern recognitionor data classification, through a learning process. Neural networks simulate biological systems, `where learning involves adjustments to thesynaptic connections between neurons. 6. Anatomy of ANN Neural Networks map a set ofInput 0Input 1...Input ninput-nodes to a set of output-nodes Neural Network Number of inputs/outputs is `variableOutput 0 Output 1 ... Output m The Network itself is composed ofan arbitrary number of nodes withan arbitrary topology. 6 7. Biological Background A neuron: many-inputs / one-output unit Output can be excited or not excited Incoming signals from other neurons determine if the `neuron shall excite ("fire") Output subject to attenuation in the synapses, which arejunction parts of the neuron 8. Neural Network Topologies This is of two types: Feed Forward Neural Networks: Unidirectional, No feedback, No cycles. ` Recurrent Network: Bi-directional, feedback. 9. Training Of ANNA neural network has to be configured such that the application of a set of inputs produces the desired set of outputs.`Train the neural network by feeding it teaching patterns and letting it change its weights according to some learning rule. 10. Neural Network in Data Mining Feed Forward Neural Network:The simplified process for training a FFNN is as follows:1. Input data is presented to the network and propagated `through the network until it reaches the output layer. Thisforward process produces a predicted output.2. The predicted output is subtracted from the actual outputand an error value for the networks is calculated. 11. Neural Network in Data Mining3. The neural network then uses supervised learning, which inmost cases is back propagation, to train the network. Backpropagation is a learning algorithm for adjusting the `weights. It starts with the weights between the output layerPEs and the last hidden layer PEs and works backwardsthrough the network.4. Once back propagation has finished, the forward process 12. Neural Network in Data Mining Back Propagation: Is a common method of teaching artificial neural networks how to perform a given task. The back ` propagation algorithm is used in layered feedforward ANNs. The back propagation algorithm uses supervised learning, which means that we provide the algorithm 13. Neural Network in Data MiningTechnique used:1. Present a training sample to the neural network.2. Compare the networks output to the desired output from thatsample. Calculate the error in each output neuron. `3. For each neuron, calculate what the output should have been, anda scaling factor, how much lower or higher the output must beadjusted to match the desired output. This is the local error. 14. Neural Network in Data Mining4. Adjust the weights of each neuron to lower the local error.5. Assign "blame" for the local error to neurons at the` previous level, giving greater responsibility to neurons connected by stronger weights.6. Repeat the steps above on the neurons at the 15. Basics of a Node Input 0 Input 1 ... Input n A node is an W0W1... Wn element whichWb+ + performs a function`fH(x) Connection y = fH((wixi) + Wb)OutputNode 15 16. Simple Perceptron Binary logicInput 0 Input 1application W0W1 fH(x) [linear threshold] ` Wb+ Wi = random(-1,1) fH(x) Y = u(W0X0 + W1X1Output+ Wb) 16 17. Algorithm1. Initialize the weights in the network (often randomly)2. repeat * for each example e in the training set do 1. O = neural-net-output(network, e) ; forward pass 2. T = teacher output for e 3. Calculate error (T - O) at the output units 4. Compute delta_wi for all weights ` from hidden layer to output layer ; backward pass 5. Compute delta_wi for all weights from input layer to hidden layer ; backward pass continued 6. Update the weights in the network * end3. until all examples classified correctly orstopping criterion satisfied4. return(network) 18. Advantages High Accuracy: Neural networks are able to approximate complexnon-linear mappings Noise Tolerance: Neural networks are very flexible with respect toincomplete, missing and noisy data. ` Independence from prior assumptions: Neural networks do notmake a priori assumptions about the distribution of the data, or theform of interactions between factors. Ease of maintenance: Neural networks can be updated with freshdata, making them useful for dynamic environments. 19. Applications Finance. Marketing. Human Resource. ` Accounting. 20. Design Problems There are no general methods to determine theoptimal number of neurons necessary for solvingany problem.` It is difficult to select a training data set whichfully describes the problem to be solved. 21. Improving ANN Designing Neural Networks using Genetic Algorithms. Neuro-Fuzzy Systems. ` 22. Conclusion There is rarely one right tool to use in data mining; it is a question as to what is available and what gives the best results. Many ` articles, in addition to those mentioned in this paper, consider neural networks to be a promising data mining tool 23. Thank you