Ci

Computational Intelligence FACULTY NAME: Dr. Santosh Kumar Majhi SCRIBED BY: Pranati Pradhan Regd no- 1805040002

Single layer neural network:  This type of network comprises of two layer, namely the input layer and the output layer.  The input layer neurons receive the input signals and the output layer neurons receive the output signals.  The synaptic links carrying the weights connect every input neuron to output neuron but not vice-versa. Such a network is termed as feedforward in type or acyclic in nature.  The input layer merely transmits the signals to the output layer. Hence the name single layer feedforward network.

xi =Input neurons yi=Output neurons wij=Weights

Multilayer neural network:  The concept is of feedforward ANN having more than one weighted layer. As this network has one or more layers between the input and the output layer, it is called hidden layers.  The computational units of hidden layer are known as hidden neurons or hidden units.  The input layer neurons are linked to the hidden layer neurons and the weights on these links are referred to as input-hidden layer weights.  Again the hidden layer neurons are linked to the output layer neurons and corresponding weights are referred to as hidden-output layer weights.

Xi=Input neurons yj =Hidden neurons zk=Output neurons Vij =Input hidden layer weights Wjk =Output hidden layer weights

Recurrent network:  These networks differ from feedforward network architectures in the sense that there is at least one feedback loop.  Thus in these networks, for example there could exist one layer with feedback connections as shown in the figure.

 There could also be neurons with self feedback links i.e. the output of a neuron is fed back into itself as input.