Neural networks
Download as PPT, PDF1 like305 views
This document provides an introduction to neural networks. It defines neural networks as systems composed of simple processing elements that operate in parallel and whose function is determined by the network structure and connection strengths. Neural networks aim to mimic the human brain by acquiring knowledge through a learning process and storing it in the strengths of connections between neurons. The document then discusses the biological foundations of neural networks and how artificial neural networks are modeled after biological neural networks. It also outlines common neural network architectures, training processes, activation functions, and applications.
Neural networks
- 1. 4/3/2020 1 INTRODUCTION TO NEURAL NETWORKS BY Mr.A.Arulkumar, Assistant Professor Dept. of Mechatronics Engg Kamaraj College of Engg &Technology Email : arulkumarmtr@kamarajengg.edu.in
- 2. 4/3/2020 2 DEFINITION OF NEURAL NETWORKS According to the DARPA Neural Network Study (1988, AFCEA International Press, p. 60): • ... a neural network is a system composed of many simple processing elements operating in parallel whose function is determined by network structure, connection strengths, and the processing performed at computing elements or nodes.
- 3. 4/3/2020 3 According to Haykin (1994), p. 2: • A neural network is a massively parallel distributed processor that has a natural propensity for storing experiential knowledge and making it available for use. It resembles the brain in two respects: – Knowledge is acquired by the network through a learning process. – Interneuron connection strengths known as synaptic weights are used to store the knowledge.
- 4. 4/3/2020 4 BRAIN COMPUTATION The human brain contains about 10 billion nerve cells, or neurons. On average, each neuron is connected to other neurons through approximately 10,000 synapses.
- 6. 4/3/2020 6 BIOLOGICAL (MOTOR) NEURON
- 7. 4/3/2020 7 • Information-processing system. • Neurons process the information. • The signals are transmitted by means of connection links. • The links possess an associated weight. • The output signal is obtained by applying activations to the net input. ARTIFICIAL NEURAL NET
- 8. 4/3/2020 8 MOTIVATION FOR NEURAL NET • Scientists are challenged to use machines more effectively for tasks currently solved by humans. • Symbolic rules don't reflect processes actually used by humans. • Traditional computing excels in many areas, but not in others.
- 9. 4/3/2020 9 The major areas being: • Massive parallelism, • Distributed representation and computation, • Learning ability, • Generalization ability, • Adaptivity, • Inherent contextual information processing, • Fault tolerance, • Low energy consumption.
- 10. 4/3/2020 10 ARTIFICIAL NEURAL NET X2 X1 W2 W1 Y The figure shows a simple artificial neural net with two input neurons (X1, X2) and one output neuron (Y). The inter connected weights are given by W1 and W2.
- 11. 4/3/2020 11 ASSOCIATION OF BIOLOGICAL NET WITH ARTIFICIAL NET
- 12. 4/3/2020 12 The neuron is the basic information processing unit of a NN. It consists of: 1. A set of links, describing the neuron inputs, with weights W1, W2, …, Wm. 2. An adder function (linear combiner) for computing the weighted sum of the inputs (real numbers): 3. Activation function for limiting the amplitude of the neuron output. j j jXWu m 1 )(uy b PROCESSING OF AN ARTIFICIAL NET
- 13. 4/3/2020 13 BIAS OF AN ARTIFICIAL NEURON The bias value is added to the weighted sum ∑wixi so that we can transform it from the origin. Yin = ∑wixi + b, where b is the bias x1-x2=0 x1-x2= 1 x1 x2 x1-x2= -1
- 14. 4/3/2020 14 MULTI LAYER ARTIFICIAL NEURAL NET INPUT: records without class attribute with normalized attributes values. INPUT VECTOR: X = { x1, x2, …, xn} where n is the number of (non-class) attributes. INPUT LAYER: there are as many nodes as non- class attributes, i.e. as the length of the input vector. HIDDEN LAYER: the number of nodes in the hidden layer and the number of hidden layers depends on implementation.
- 15. 4/3/2020 15 OPERATION OF A NEURAL NET - f Weighted sum Input vector x Output y Activation function Weight vector w w0j w1j wnj x0 x1 xn Bias
- 16. 4/3/2020 16 WEIGHT AND BIAS UPDATION Per Sample Updating - updating weights and biases after the presentation of each sample. Per Training Set Updating (Epoch or Iteration) - weight and bias increments could be accumulated in variables and the weights and biases updated after all the samples of the training set have been presented.
- 17. 4/3/2020 17 STOPPING CONDITION • All change in weights (wij) in the previous epoch are below some threshold, or • The percentage of samples misclassified in the previous epoch is below some threshold, or • A pre-specified number of epochs has expired. • In practice, several hundreds of thousands of epochs may be required before the weights will converge.
- 18. 4/3/2020 18 BUILDING BLOCKS OF ARTIFICIAL NEURAL NET Network Architecture (Connection between Neurons) Setting the Weights (Training) Activation Function
- 19. 4/3/2020 19
- 20. 4/3/2020 20 LAYER PROPERTIES • Input Layer: Each input unit may be designated by an attribute value possessed by the instance. • Hidden Layer: Not directly observable, provides nonlinearities for the network. • Output Layer: Encodes possible values.
- 21. 4/3/2020 21 TRAINING PROCESS Supervised Training - Providing the network with a series of sample inputs and comparing the output with the expected responses. Unsupervised Training - Most similar input vector is assigned to the same output unit. Reinforcement Training - Right answer is not provided but indication of whether ‘right’ or ‘wrong’ is provided.
- 22. 4/3/2020 22 DEFINITION OF SUPERVISED LEARNING NETWORKS • Training and test data sets • Training set; input & target are specified
- 23. 4/3/2020 23 UNSUPERVISED LEARNING No help from the outside. No training data, no information available on the desired output. Learning by doing. Used to pick out structure in the input: • Clustering, • Reduction of dimensionality compression. Example: Kohonen’s Learning Law.
- 24. 4/3/2020 24 ACTIVATION FUNCTION ACTIVATION LEVEL – DISCRETE OR CONTINUOUS HARD LIMIT FUCNTION (DISCRETE) Binary Activation function Bipolar activation function Identity function SIGMOIDAL ACTIVATION FUNCTION (CONTINUOUS) Binary Sigmoidal activation function Bipolar Sigmoidal activation function
- 25. 4/3/2020 25 ACTIVATION FUNCTION Activation functions: (A)Identity (B)Binary step (C)Bipolar step (D)Binary sigmoidal (E)Bipolar sigmoidal (F)Ramp
- 26. 4/3/2020 26 CONSTRUCTING ANN •Determine the network properties: •Network topology •Types of connectivity •Order of connections •Weight range •Determine the node properties: •Activation range •Determine the system dynamics •Weight initialization scheme •Activation – calculating formula •Learning rule
- 27. 4/3/2020 27 PROBLEM SOLVING Select a suitable NN model based on the nature of the problem. Construct a NN according to the characteristics of the application domain. Train the neural network with the learning procedure of the selected model. Use the trained network for making inference or solving problems.
- 28. 4/3/2020 28 NEURAL NETWORKS Neural Network learns by adjusting the weights so as to be able to correctly classify the training data and hence, after testing phase, to classify unknown data. Neural Network needs long time for training. Neural Network has a high tolerance to noisy and incomplete data.
- 29. 4/3/2020 29 SALIENT FEATURES OF ANN •Adaptive learning •Self-organization •Real-time operation •Fault tolerance via redundant information coding •Massive parallelism •Learning and generalizing ability •Distributed representation
- 30. 4/3/2020 30 McCULLOCH–PITTS NEURON Neurons are sparsely and randomly connected Firing state is binary (1 = firing, 0 = not firing) All but one neuron are excitatory (tend to increase voltage of other cells) -One inhibitory neuron connects to all other neurons -It functions to regulate network activity (prevent too many firings)
- 31. 4/3/2020 31 LINEAR SEPARABILITY Linear separability is the concept wherein the separation of the input space into regions is based on whether the network response is positive or negative. Consider a network having positive response in the first quadrant and negative response in all other quadrants (AND function) with either binary or bipolar data, then the decision line is drawn separating the positive response region from the negative response region.
- 32. 4/3/2020 32 HEBB NETWORK Donald Hebb stated in 1949 that in the brain, the learning is performed by the change in the synaptic gap. Hebb explained it: “When an axon of cell A is near enough to excite cell B, and repeatedly or permanently takes place in firing it, some growth process or metabolic change takes place in one or both the cells such that A’s efficiency, as one of the cells firing B, is increased.”
- 33. 4/3/2020 33 • The weights between neurons whose activities are positively correlated are increased: • Associative memory is produced automatically )x,x(ncorrelatio~ dt dw ji ij HEBB LEARNING The Hebb rule can be used for pattern association, pattern categorization, pattern classification and over a range of other areas.
- 34. 4/3/2020 34 FEW APPLICATIONS OF NEURAL NETWORKS