Error using feedforwardnet (line 72) FCN does not return an info object.

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

Answer 1

[Jan]

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.