Error using feedforwardnet (line 72) FCN does not return an info object.
7 views (last 30 days)
Show older comments
Hello,
With this code:
% Configuration:
alg1 = 'nnd9mc';% First training algorithm to use
H = 50;% Number of neurons in the hidden layer
delta_epochs = [1,14,985];% Number of epochs to train in each step
epochs = cumsum(delta_epochs);
%generation of examples and targets
dx=0.05;% Decrease this value to increase the number of data points
x=0:dx:3*pi;
y=sin(x.^2);
sigma=0.2;% Standard deviation of added noise
yn=y+sigma*randn(size(y));% Add gaussian noise
t=yn;% Targets. Change to yn to train on noisy data
plot(X,t);
hold on;
net1=feedforwardnet(H,alg1);% Define the feedfoward net (hidden layers)
I have got the following error:
Error using feedforwardnet (line 72)
FCN does not return an info object.
I executed theses lines in the command window (advice from another post):
rehash toolboxcache
restoredefaultpath
But I still get the error, any one know where it comes from ?
Regards
0 Comments
Answers (1)
Jan
on 20 Mar 2021
According to the documenation: https://www.mathworks.com/help/deeplearning/ref/feedforwardnet.html#mw_85a847e7-13dd-45fd-b7b9-06068e8f5937 the char vector 'nnd9mc' is not accepted as trainFcn.
0 Comments
See Also
Categories
Find more on Define Shallow Neural Network Architectures in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!