Explain Classification by Backpropagation/ Backpropagation.

CLASSIFICATION BY BACKPROPAGATION

Backpropagation is a neural network learning algorithm. Psychologists originally kindled the field of neural networks and neurobiologists sought to develop and test computational analogs of neurons. Roughly speaking, a neural network is a set of connected input/output units where each connection has a weight associated with it. During the learning phase, the network learns by Neural network learning is also referred to as connectionist learning due to the connections between adjusting the weights so as to be able to predict the correct class label of the input samples. units. The most popular neural network algorithm is the backpropagation algorithm, A neural network or artificial neural network (ANN) is composed of a number of nodes or units connected by links. advantages of neural networks, however, include their high tolerance of noisy data as well as their ability to classify patterns on which they have not been trained. Each link has a numeric weight associated with it as shown in figure 6.7 below.

Actually, artificial neural networks are programs designed to solve any problem by trying to mimic the structure and the function of our nervous system. Generally, Input to the network is represented by the mathematical symbol X₁ Each of these inputs are multiplied by a connection weight, We. These products are simply summed, fed through the transfer function f() to generate results as output.

                                             OR,

Backpropagation

• Backpropagation is a neural network learning algorithm that gained repute in the 1980s.

• Backpropagation learns by iteratively processing a data set of training tuples, comparing the network’s prediction for each tuple with the actual known target value.

• The target value may be the known class label of the training tuple (for classification problems) or a continuous value (for prediction).

• For each training tuple, the weights are modified so as to minimize the mean squared error between the network’s prediction and the actual target value.

• These modifications are made in the “backward” direction, that is, from the output layer, through each hidden layer down to the first hidden layer (hence the name backpropagation).

• Although it is not guaranteed, in general, the weights will eventually converge, and the learning process stops.

Steps in Backpropagation:

– Initialize weights (too small random numbers) and biases in the network

– Propagate the inputs forward (by applying activation function)

– Backpropagate the error (by updating weights and biases)

– Terminating condition (when error is very small, etc.)