MATLAB: How to specify some weight of ANN

neural networkspeiciyweight

Is there a way to specify some weights of ANN, as I build a parallel ANN structure, and the output of the whole ANN is the summary of sub-ANN, say Out=Out1+Out2-Out3,so the weight of the output neuron are 1,1,-1. My question is: can I specify these three weights, while the other weights will be updated automatically?

Best Answer

Set the learning rates of the output layer to zero.

Related Solutions

MATLAB: ANN

we use the SIM function to see the predicted response of the ANN.

MATLAB: How to create target matrix for ANN

The target matrix for a c-class classifier should contain {0,1} unit vector columns from the unit matrix eye(c). The functions IND2VEC and VEC2IND are used to convert from trueclassindices to target vectors and from output vectors to estimatedclassindices.

 help ind2vec
 doc ind2vec
 help vec2ind
 doc vec2ind

Examples:

 trueclassindices = [ 1 5 2 4 3 ]
 target = full(ind2vec([trueclassindices]))
 output = fliplr(target)
 estimatedclassindices =  vec2ind(output)

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: ANN

MATLAB: How to create target matrix for ANN

Related Question