classification by backpropagation

Neural Networks

 

•A set of connected input/output units where each connection has
•a weight associated with it
•Advantages
–prediction accuracy is generally high
–robust, works when training examples contain errors
–output may be discrete, real-valued, or a vector of several discrete or real-valued attributes
–fast evaluation of the learned target function
•Criticism
–long training time
–require (typically empirically determined) parameters (e.g. network topology)
–difficult to understand the learned function (weights)
–not easy to incorporate domain knowledge

 

A  Neuron

 

 

 

•The n-dimensional input vector x is mapped into  variable y by means of the scalar product and a nonlinear function mapping

 

 

Network Training

 

•The ultimate objective of training
–obtain a set of weights that makes almost all the tuples in the training data classified correctly
•Steps
–Initialize weights with random values
–Feed the input tuples into the network one by one
–For each unit
•Compute the net input to the unit as a linear combination of all the inputs to the unit
•Compute the output value using the activation function
•Compute the error
•Update the weights and the bias

 

 

See More

classification and prediction by v. vanthana