RBF ,LVQ in NN

1 view (last 30 days)
Yogini Prabhu
Yogini Prabhu on 5 Mar 2021
Commented: Yogini Prabhu on 29 Mar 2021
I made a NN of MLP, which was developed using nprtool of MATLAB.I have the generated matlab code with me, now. it classifies 4 classes.
Now Ii want to implement NN for other types -RBF ,LVQ . what are the changes required?

Answers (2)

Yogini Prabhu
Yogini Prabhu on 16 Mar 2021
I have made a NN of MLP, which was developed using nprtool of MATLAB.I have the generated matlab code with me, now. it classifies 4 classes.
Now Ii want to implement NN for other types -RBF ,LVQ . what are the changes required?

Pratyush Roy
Pratyush Roy on 29 Mar 2021
Hi Yogini,
A RBF neural network consists of a radial basis layer followed by a linear layer. You can assign the "radbas" transfer function to the first hidden layer of the MLP to convert it to a RBF neural network.
Similarly, a LVQ neural network consists of a competitive layer followed by a linear layer. Assigning the "compet" transfer function to the first hidden layer of the MLP converts it to a LVQ neural network.
You can also refer to dedicated functions like lvqnet (or LVQ and newrbe for RBE.
Hope this helps!
  1 Comment
Yogini Prabhu
Yogini Prabhu on 29 Mar 2021
thanks for very informative reply

Sign in to comment.

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!