Displaying MSE values at training,validation and testing ratios

6 次查看（过去 30 天）
bryce maher
bryce maher 2020-2-23
回答： Vimal Rathod 2020-2-26
Just started learning about neural networks and have been using the neural net fitting tool box. I've taken the code and tried adding an extra layer which has been successful but i dont know how to find these MSE values?
heres my code:
% Solve an Input-Output Fitting problem with a Neural Network
% Pressure - input data.
% Output - target data.
input=xlsread('NEW DATA.xlsx',1,'E7:E39');
x = input';
output=xlsread('NEW DATA.xlsx',1,'H7:I39');
t = output';
% Choose a Training Function
trainFcn = 'trainlm'; % Levenberg-Marquardt backpropagation.
% Create a Fitting Network
hiddenLayer1Size = 80;
hiddenLayer2Size = 40;
net = fitnet([hiddenLayer1Size hiddenLayer2Size],trainFcn);
% Setup Division of Data for Training, Validation, Testing
net.divideParam.trainRatio = 80/100;
net.divideParam.valRatio = 5/100;
net.divideParam.testRatio = 15/100;
% Train the Network
[net,tr] = train(net,x,t);
% Test the Network
y = net(x);
e = gsubtract(t,y);
performance = perform(net,t,y)
view(net)

请先登录，再回答此问题。

回答（1 个）

Vimal Rathod
Vimal Rathod 2020-2-26
Hi,
Below is a link to similar question which could be of your use.
https://www.mathworks.com/matlabcentral/answers/405606-how-to-calculate-the-mse-for-multi-output-neural-network
Hope this helps!

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

Community Treasure Hunt

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

Start Hunting!

Translated by