how to initialize the neural network to a set of weights ???
조회 수: 24 (최근 30일)
이전 댓글 표시
I created my NN with patternet ??
댓글 수: 0
채택된 답변
Greg Heath
2012년 10월 20일
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
댓글 수: 2
Samisam
2018년 1월 7일
@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??
추가 답변 (3개)
Greg Heath
2012년 10월 19일
편집: Greg Heath
2012년 10월 20일
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
댓글 수: 4
LukasJ
2020년 11월 6일
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
renz
2012년 10월 19일
net.IW{1} = %input weights
net.LW{2} = %layer weights
% biases:
net.b{1} =
net.b{2} =
댓글 수: 0
Sara Perez
2019년 9월 12일
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:
댓글 수: 0
참고 항목
카테고리
Help Center 및 File Exchange에서 Sequence and Numeric Feature Data Workflows에 대해 자세히 알아보기
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!