Learning By Example

Description:-Consider the Multi-layer feed-forward back-propagation network below. The subscripts I, H, O denotes input, hidden and output neurons. The weight of the arc between i^th input neuron to j^th hidden layer is V_ij .The weight of the arc between i^th hidden neuron to j th out layer is W_ij

The table below indicates an 'nset' of input and output data. It shows ℓ inputs and the corresponding n output data.

Computation of Input Layers

• Input Layer Computation

Consider linear activation function. If the output of the input layer is the input of the input layer and the transfer function is 1, then

{O}I = {I} I

ℓ x 1    ℓ x 1 (denotes matrix row, column size)

The hidden neurons are connected by synapses to the input neurons.

- Let V_ij be the weight of the arc between i^th input neuron to j^th hidden layer.

- The input to the hidden neuron is the weighted sum of the outputs of the input neurons. Thus the equation

Denotes weight matrix or connectivity matrix between input neurons and a hidden neurons as [ V ].

We can get an input to the hidden neuron as ℓ x m