Deep Learning Layers to increase training accuracy

3 次查看(过去 30 天)
Hi everyones.
I want to use DL for modeling a problem with 6 inputs and one output.
I've used the following layers but I cannot increase the model accuracy not only for unseen samples but also for training samples.
I've check different structures and try to generated a complex model as much as possible to get at least good results in training stages
numHiddenNeuron = 100;
layers = [
featureInputLayer(numFeatures,'Normalization','rescale-symmetric')
fullyConnectedLayer(numHiddenNeuron)
reluLayer('Name','relu')
batchNormalizationLayer
fullyConnectedLayer(numOut)
regressionLayer('Name','regression')];
I would be appreciated it if you could help me.
Regards,

回答(1 个)

yanqi liu
yanqi liu 2022-2-23
yes,sir,may be add some dropoutLayer in net Layers,such as
numHiddenNeuron = 100;
layers = [
featureInputLayer(numFeatures,'Normalization','rescale-symmetric')
fullyConnectedLayer(numHiddenNeuron)
reluLayer('Name','relu')
batchNormalizationLayer
dropoutLayer
fullyConnectedLayer(numOut)
regressionLayer('Name','regression')];
% or
layers = [ ...
sequenceInputLayer(numFeatures)
lstmLayer(100,'OutputMode','sequence')
dropoutLayer(0.3)
lstmLayer(50,'OutputMode','sequence')
dropoutLayer(0.2)
fullyConnectedLayer(numOut)
regressionLayer];
if possible,may be upload your data to analysis
  2 个评论
Jahetbe
Jahetbe 2022-2-23
Thank you for your response.
I've check the first one and the results didn't change.
For the 2nd one, my data is not time series and I cannot use the "sequenceInputLayer" as well as "lstmLayer".
Dou you have any other recommendation? Infortunately the resutls are vey bad
Regards
Jahetbe
Jahetbe 2022-2-23
I've check it agsin, unfortunately after some iterations (lest than 20), the RMSE does not decrease

请先登录,再进行评论。

类别

Help CenterFile Exchange 中查找有关 Deep Learning Toolbox 的更多信息

Community Treasure Hunt

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

Start Hunting!

Translated by