# how to initialize the neural network to a set of weights ???

34 vues (au cours des 30 derniers jours)
Mariem Harmassi le 16 Oct 2012
Commenté : LukasJ le 6 Nov 2020
I created my NN with patternet ??
##### 0 commentairesAfficher -2 commentaires plus anciensMasquer -2 commentaires plus anciens

Connectez-vous pour commenter.

### Réponse acceptée

Greg Heath le 20 Oct 2012
Unlike the older nets (e.g., newfit, newpr, newff,...), you cannot assign weights to the newer networks (e.g., fitnet, patternnet, feedforwardnet,...) unless the net is configured.
There are two ways to configure the net before manually assigning your own initial weights. Both will assign initial weights that you can overwrite:
1. help/doc configure.
net = configure(net, x, t );
2. Train the net for 1 epoch
net.trainParam.epochs= 1.
net = train(net,x,t);
Hope this helps.
Thank you for formally accepting my answer.
Greg
##### 2 commentairesAfficher AucuneMasquer Aucune
Mariem Harmassi le 20 Oct 2012
ok i will try to cinfigure the net before training cauz the second solution is not a good one i need to train the net according to a specifical set of weignts .
Samisam le 7 Jan 2018
@Greg Heath can I do a manual weight initialization before I train the net???
I mean if I have an optimal weight from a spesific algorithm and I want to create a NN to test data using these weights is there any way to do this without training the net again??

Connectez-vous pour commenter.

### Plus de réponses (3)

Greg Heath le 19 Oct 2012
Modifié(e) : Greg Heath le 20 Oct 2012
net = patternet;
will default to H = 10 hidden nodes. For other values use
net = patternnet(H);
If
size(input) = [I N ]
size(target) = [O N ]
the node topology is I-H-O.
For a manual weight initialization, first configure the net:
net = configure(net,x,t);
For a random weight initialization, initialize the random number generator. Then generate and assign the weights:
rng(0)
IW = 0.01*randn(H,I);
b1 = 0.01*randn(H,1);
LW = 0.01*randn(O,H);
b2 = 0.01*randn(O,1);
then
net.IW{1,1} = IW;
net.b{1,1} = b1;
net.LW{2,1} = LW;
net.b{2,1} = b2;
Hope this helps.
Thank you for formally accepting my answer.
Greg
##### 4 commentairesAfficher 2 commentaires plus anciensMasquer 2 commentaires plus anciens
Heather Zhang le 30 Août 2016
Thank you Greg. "configure" works really well.
LukasJ le 6 Nov 2020
Dear Greg Heath,
unfortunately configuring the net doesn't do the trick for me:
I tried setting the inital weights manually e.g.
net.iw{1,1} = zeros(...
and via
net.initFcn = 'initlay';
net.layers{1,1}.initFcn = 'initwb';
net.layers{2,1}.initFcn = 'initwb';
net.InputWeights{1,1}.initFcn = 'midpoint';
net.LayerWeights{2,1}.initFcn = 'midpoint';
initFcn to call for midpoint initialization. The first won't update any weights after training, the former won't do anything (still random weights when I check before training, training results after fixed epochs are not comparable).
Your help would be very much appreciated!
Best regards,
Lukas

Connectez-vous pour commenter.

renz le 19 Oct 2012
net.IW{1} = %input weights
net.LW{2} = %layer weights
% biases:
net.b{1} =
net.b{2} =
##### 0 commentairesAfficher -2 commentaires plus anciensMasquer -2 commentaires plus anciens

Connectez-vous pour commenter.

Sara Perez le 12 Sep 2019
You can specify your own function for the initialization of the weights with 'WeightsInitializer' in convolution2dLayer.
layer = convolution2dLayer(filterSize,numFilters, ...
'WeightsInitializer', @(sz) rand(sz) * 0.0001, ...
'BiasInitializer', @(sz) rand(sz) * 0.0001)
info here:
##### 0 commentairesAfficher -2 commentaires plus anciensMasquer -2 commentaires plus anciens

Connectez-vous pour commenter.

### Catégories

En savoir plus sur Sequence and Numeric Feature Data Workflows dans Help Center et File Exchange

### Community Treasure Hunt

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

Start Hunting!

Translated by