Neural network weight and bias initializaiton problem
2 views (last 30 days)
Show older comments
Hi.
I'm cresting a neural network in one part of my program and using it's weights and biases for another neural network in other part so I have these codes:
net_b = patternnet(10);
net_b = configure(net,INPUT,Target);
Weights = getwb(net);
I will use this neural network weights and biases for creating another neural network as below:
net = patternnet(10);
net = configure(net,INPUT,Target);
net = setwb(net,Weights);
Everything is good until this stage but now I want disable pre-processing from neural network (Because I did it in one of stages of my program before insert the data to the neural network) So I will use these functions:
net.inputs{1}.processFcns={};
net.outputs{2}.processFcns={};
When I use two above functions to remove processing and after that check weights in inputs layer or biases in output layer everything will remove and I have an empty matrix but in hidden layer everything is normal. How can I do these without removing my weights and biases?
Thanks.
0 Comments
Accepted Answer
Greg Heath
on 14 Aug 2014
net = patternnet(10);
net.inputs{1}.processFcns = {};
net.outputs{2}.processFcns = {};
net = configure(net,INPUT,Target);
net = setwb(net,Weights);
IW = net.IW
b = net.b
LW = net.LW
Hope this helps.
Thank you for formally accepting my answer
Greg
More Answers (0)
See Also
Categories
Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!