In machine learning, a neural network (also artificial neural network or neural net, abbreviated ANN or NN) is a computational model inspired by the structure and functions of biological neural networks

In machine learning, a neural network (also artificial neural network or neural net, abbreviated ANN or NN) is a computational model inspired by the structure and functions of biological neural networks

• 1.
  Neural Networks  Amodel of reasoning based on the human brain  complex networks of simple computing elements  capable of learning from examples • with appropriate learning methods  collection of simple elements performs high-level operations
• 3.
  Neural Networks andthe Brain (Cont.)  The human brain incorporates nearly 10 billion neurons and 60 trillion connections between them.  Our brain can be considered as a highly complex, non-linear and parallel information-processing system.  Learning is a fundamental and essential characteristic of biological neural networks.
• 4.
  Artificial Neuron Diagram weighted inputs are summed up by the input function  the (nonlinear) activation function calculates the activation value, which determines the output [Russell & Norvig, 1995]
• 5.
  Similarity with BiologicalNetwork • Fundamental processing element of a neural network is a neuron • A human brain has 100 billion neurons • An ant brain has 250,000 neurons
• 6.
  Neural Network  NeuralNetwork is a set of connected INPUT/OUTPUT UNITS, where each connection has a WEIGHT associated with it.  Neural Network learning is also called CONNECTIONIST learning due to the connections between units.  It is a case of SUPERVISED, INDUCTIVE or CLASSIFICATION learning.
• 7.
  Neural Network  NeuralNetwork 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
• 8.
  One Neuron asa Network
• 9.
  One Neuron asa Network  Here x1 and x2 are normalized attribute value of data.  y is the output of the neuron , i.e the class label.  x1 and x2 values multiplied by weight values w1 and w2 are input to the neuron x.  Value of x1 is multiplied by a weight w1 and values of x2 is multiplied by a weight w2.  Given that • w1 = 0.5 and w2 = 0.5 • Say value of x1 is 0.3 and value of x2 is 0.8, • So, weighted sum is : • sum= w1 x x1 + w2 x x2 = 0.5 x 0.3 + 0.5 x 0.8 = 0.55
• 10.
  One Neuron asa Network • The neuron receives the weighted sum as input and calculates the output as a function of input as follows : • y = f(x) , where f(x) is defined as • f(x) = 0 { when x< 0.5 } • f(x) = 1 { when x >= 0.5 } • For our example, x ( weighted sum ) is 0.55, so y = 1 , • That means corresponding input attribute values are classified in class 1. • If for another input values , x = 0.45 , then f(x) = 0, • so we could conclude that input values are classified to class 0.
• 11.
  Bias of aNeuron  We need the bias value to be added to the weighted sum ∑wixi so that we can transform it from the origin. v = ∑wixi + b, here b is the bias x1-x2=0 x1-x2= 1 x1 x2 x1-x2= -1
• 12.
  Bias as extrainput Input Attribute values weights Summing function Activation function v Output class y x1 x2 xm w2 wm W1    ) (  w0 x0 = +1 b w x w v j m j j    0 0
• 13.
  Neuron with Activation 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.    m 1 j jx w u j ) (u y b  
• 16.
  k O jk w Output nodes Input nodes Hiddennodes Output Class Input Record : xi wij - weights Network is fully connected j O A Multilayer Feed-Forward Neural Network
• 17.
  Neural Network  Theinputs are fed simultaneously into the input layer.  The weighted outputs of these units are fed into hidden layer.  The weighted outputs of the last hidden layer are inputs to units making up the output layer.
• 18.
  Question ???  Questionsand Comments are welcome…  ?  THANKS  Have a great Day !