What's wrong with my neural network?

4 visualizaciones (últimos 30 días)
Tony Stark
Tony Stark el 26 de Oct. de 2022
Respondida: Amanjit Dulai el 27 de Oct. de 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);

Respuesta aceptada

Amanjit Dulai
Amanjit Dulai el 27 de Oct. de 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.

Más respuestas (0)

Productos


Versión

R2021b

Community Treasure Hunt

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

Start Hunting!

Translated by