Weights

Top 

Weights

As neurons pass values from one layer of the network to the next layer in backpropagation networks, the values are modified by a weight value in the link that represents connection strengths between the neurons.

 

When the network is designed in the Architecture and Parameters module, the weights begin as random numbers that fall within a range specified in the module.  As each pattern passes though the network, the weight is raised to positively reinforce a connection.  To negatively reinforce or inhibit a connection, the weight is lowered.