What's wrong with my neural network?
7 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Tony Stark
le 26 Oct 2022
Réponse apportée : Amanjit Dulai
le 27 Oct 2022
I am trying to debug and figure out why my code is not getting better with each epoch, rather it's getting progressively worse.
I am trying to make it so that I get better training of my training data each time I run the code. What do I do to fix it?
In general, I am aiming for 11 inputs, 1 single layer, and 5 output layers. I'm not sure what's the problem.
Here is the lines of code:
x = rand(75,11);
y = randi(5, 5, 75);
P = x';
T = y;
net = linearlayer;
net = configure(net,P,T);
net.IW{1}(5,11);
net.b{1};
[net,a,e,pf] = adapt(net,P,T);
net = train(net,P,T);
0 commentaires
Réponse acceptée
Amanjit Dulai
le 27 Oct 2022
I managed to get this to work by reducing the learning rate:
x = rand(75,11);
y = randi(5, 5, 75);
P = x';
T = y;
% Set the learning rate to 0.001
net = linearlayer(0,0.001);
net = configure(net,P,T);
net.IW{1}(5,11);
net.b{1};
[net,a,e,pf] = adapt(net,P,T);
net = train(net,P,T);
By default, linearlayer does not use backpropagation when training. Instead, it uses the Widrow-Hoff learning rule, so the training might behave differently compared to other networks (fitnet for example uses backpropagation by default).
It's also worth noting that linearlayer is learning only a linear function (that is, a weight and a bias), so it won't fit data with a non-linear relationship very well.
0 commentaires
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Define Shallow Neural Network Architectures dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!