biological neuron systems. Neural networks are typically organized in layers. Layers are made up of a number of interconnected 'nodes' .which contain an 'activation function'. Patterns are presented to the network via the 'input layer', which communicates to one or more 'hidden layers' where the actual processing is done via a system of weighted 'connections'. The hidden layers then link to an 'output layer' where the answer is output
nervous system should be able to produce similar responses and behaviours in artificial systems. The nervous system is build by relatively simple units, the neurons, so copying their behaviour and functionality should be the solution.
weights, thresholds and a single activation function A set or connection link: each of which is characterized by a weight or strength of its own wkj . Specifically, a signal xj at the input synapse „j‟connected to neuron „k‟is multiplied by the synaptic wkj An adder: For summing the input signals, weighted by respective synaptic strengths of the neuron in a linear operation. I w1 x1 n w2 x2 ....... wn xn w i xi i 1
input for each neuron is the sum of the weighted inputs to the neuron minus its threshold value. This is then passed through the sigmoid function. The equation for the transition in a neuron is : a = 1/(1 + exp(- x)) where x = ai wi - Q a is the activation for the neuron ai is the activation for neuron i wi is the weight Q is the threshold subtracted
performs a mathematical operation on the signal output. The most common activation functions are: - Linear Function, - Threshold Function, - Sigmoidal (S shaped) function, The activation functions are chosen depending upon the type of problem to be solved by the network.
Function (S-shape function):- The nonlinear curved S-shape function is called the sigmoid function. This is most common type of activation used to construct the neural networks. It is mathematically well behaved, differentiable and strictly increasing function. This is explained as ≈ 0 for large -ve input values, 1 for large +ve values, with a smooth transition between the two. α is slope parameter also called shape parameter symbol the λ is also used to represented this parameter. 1 Y f (I) ,0 f (I) 1 1 e 1/(1 exp( I)),0 f (I) 1 I
as a data processing system consisting of a large number of interconnected processing elements or artificial neurons. There are three fundamentally different classes of neural networks. Those are. 1. Single layer feedforward Networks. 2. Multilayer feedforward Networks. 3. Recurrent Networks. Here we have to discuss the single layer feed forward network.
single layer feed forward neural network. It consists an input layer to receive the inputs and an output layer to output the vectors. The input layer consists of „n‟ neurons, and the output layer contains „m‟ neurons . The weight of synapse connecting ith input neuron the jth output neuron is Wij. 1 2 3 4 1 2 3 Ii1 Ii2 Ii3 Iin Oi2 Oi3 Oin Oi1 W11 Io1 W21 Io2 Iom W31 Wn1 Yo1 Yo2 Yo m
layer and the outputs of the output layer is given as So Hence, the input to the output layer can be given as Because The block diagram of a single layer feed forward network. Ioj W1j II1 1 n 1 W2 j II 2 Wnj IIN Iin Ii1 Ii2 .. I m 1 o Oom ...... Oo1 Oo2 .. O I I o m 1 m n n 1 O I W T W T I n 1 m 1 II OI F(I,W) I O
broadly classified in three basic types. - Supervised Learning - Unsupervised Learning - Reinforcement Learning Supervised Learning:- In supervised learning, both the inputs and the outputs areprovided. The network then processes the inputs and compares its resulting outputs against the desired outputs Errors are then calculated, causing the system to adjust theweights which control the network. Here a teacher is assume to be present during the learning process.
is not presented to the network, Because there is no teacher to present the described patterns. So the system learns of its own by discovering and adapting to structural features of the input patterns. Reinforcement Learning:- In this method, a teacher though available, does not present the expected answer but only indicates if the computed output is correct or incorrect. The information provided helps the network in its learning process. Here a reward is given for correct answer computed and a penalty for a wrong answer.
be used torecognize handwritten characters. Image Compression:- Neural networks can receive and process vast amounts of information at once, making them useful in image compression. Stock Market Prediction:- Neural networks can examine a lot of information quickly and sort it all out, they can be used to predict stock prices. Travelling Salesman Problem:- Neural networks can solve the traveling salesman problem, but only to a certain degree of approximation. Security and Loan Applications:- With the acceptation of a neural network that will decide whether or not to grant a loan.