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

48 次查看（过去 30 天）
Mariem Harmassi
Mariem Harmassi 2012-10-16
评论： LukasJ 2020-11-6
I created my NN with patternet ??

请先登录，再回答此问题。

采纳的回答

Greg Heath
Greg Heath 2012-10-20
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 个评论
Mariem Harmassi
Mariem Harmassi 2012-10-20
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
Samisam 2018-1-7
@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??

请先登录，再进行评论。

更多回答（3 个）

Greg Heath
Greg Heath 2012-10-19
编辑：Greg Heath 2012-10-20
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 个评论
显示 2更早的评论
LukasJ
LukasJ 2020-11-6
Dear Greg Heath,
unfortunately configuring the net doesn't do the trick for me:
https://de.mathworks.com/matlabcentral/answers/589957-neural-network-not-updating-weights-after-configuration#answer_536465?s_tid=prof_contriblnk
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

请先登录，再进行评论。

renz
renz 2012-10-19
net.IW{1} = %input weights
net.LW{2} = %layer weights
% biases:
net.b{1} =
net.b{2} =
Sara Perez
Sara Perez 2019-9-12
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:
https://es.mathworks.com/help/deeplearning/ref/nnet.cnn.layer.convolution2dlayer.html

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

产品

Community Treasure Hunt

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

Start Hunting!

Translated by