How to use a custom transfer function in neural net training

53 visualizaciones (últimos 30 días)
Bob
Bob el 9 de Dic. de 2012
Editada: DGM el 23 de Feb. de 2023
I want to use a function similar to tansig. I don't seem to be able to find a good example, and the tansig.apply method only allows me one line! I'm wrapped around this axle, and I suspect I'm missing something simple. Any ideas? I'm using 2012b.

Iniciar sesión para responder a esta pregunta.

Respuesta aceptada

Greg Heath
Greg Heath el 9 de Dic. de 2012
Editada: Walter Roberson el 13 de Ag. de 2017
I cannot make sense of your post.
tanh(x) = tansig(x)
elliotsig(4*x) ~ tansig(x)
elliotsig4(x) ~ tansig(x)
function y = elliotsig4(x)
y = x./(0.25 + abs(x));
end
What do you mean by the tansig.apply method ???
Sample code would help explain.
Hope this helps.
Thank you for formally accepting my answer.
Greg
  1 comentario
Greg Heath
Greg Heath el 9 de Dic. de 2012
Editada: DGM el 23 de Feb. de 2023
Note the following ranks in speed
1. tanh
2. elliotsig4
3. elliotsig
4. tansig
function elliottime
clear all, clc
tic; for i = 1:1e4
y1 = tansig(1); % 0.7616
end; t1 = toc % 1.2259
tic; for i = 1:1e4
y2 = elliotsig(4*1); % 0.8000
end; t2= toc % 0.0029
tic; for i = 1:1e4
y3 = elliotsig4(1); % 0.8000
end; t3 = toc % 0.0027
tic; for i = 1:1e4
y4 = tanh(1); % 0.7616
end; t4 = toc % 5.94e-4
[ [ t1 t2 t3 t4 ]' [y1 y2 y3 y4 ]' ]
function y = elliotsig(x)
y = x./(1+abs(x));
end
function y = elliotsig4(x)
y = x./(0.25+abs(x));
end
end

Iniciar sesión para comentar.

Más respuestas (5)

Bob
Bob el 27 de Mzo. de 2013
mladen,
The following has worked for me.
Move a copy of feedforwardnet.m into some directory on your path. Inside, you will find an assignment that sets the type of transfer to be used. Here's a snippet:
net.layers{i}.size = param.hiddenSizes(i);
% rcl
% net.layers{i}.transferFcn = 'tansig';
% net.layers{i}.transferFcn = 'satlins';
net.layers{i}.transferFcn = 'bobfer';
end|
I invented a transfer called "bobfer". To implement it, go into .../toolbox/nnet/nnet/nntransfer.
Copy tansig.m and the folder +tansig to a directory on your path.
Give each a new name, such as bobfer.m and +bobfer.
Modify bobfer.m at the last line so it calls the bobfer.apply method:
a = bobfer.apply(n);
Now, in +bobfer, modify apply.m. This is pretty easy; it's only a few lines. This is where your transfer function goes.
Let me know if this helps...
Bob
  4 comentarios
Mostrar 2 comentarios más antiguos
Mayank Gupta
Mayank Gupta el 4 de Mayo de 2016
Can you please explain in detail how to save a custom training function to the nntool directory ? I am using Firefly algorithm for optimization.
Mehdi Jokar
Mehdi Jokar el 16 de Jul. de 2018
Bob, thank you for you instructions. but, is apply the only function that needs to be modified? or we need to modify the backprop and forwardprop function in the + folder ?
Mehdi

Iniciar sesión para comentar.

Bob
Bob el 10 de Dic. de 2012
Greg, thanks for the answer. Let me improve my question.
I wish to use a customized transfer function, that is, I have a transfer function I want to use, and it is: x = y*(1 - (0.52*abs(y/2.6))) (for -2.5<y<2.5). The reason I wish to use this is that although tansig and elliotsig work nicely for me in simulation, I am putting the NN into an FPGA, and both tansig and elliotsig are difficult for me to compute in the FPGA. The equation above is easy to compute, and easy to combine with a saturation function.
I tried to follow the advice in the documentation, but had a heck of a time trying to modify tansig.m. Within tansig.m, there's a call to tansig.apply where the tansig function is actually computed, but I eventually figured out how to modify that.
So, my question was really: how do I use an arbitrary transfer function, not one of the existing functions.
Hope this qualifies my question. Sorry to send you off on a chase timing the various transfer functions.
Thanks, /Bob/
Greg Heath
Greg Heath el 11 de Dic. de 2012
Editada: DGM el 23 de Feb. de 2023
I cannot understand why you think y2 is better than y1
x = -6:0.1:6;
y1 = x./(0.25+abs(x));
y2 = x.*(1 - (0.52*abs(x/2.6))) % (for -2.5<x<2.5).
figure
hold on
plot(x,y1)
plot(x,y2,'r')
mladen
mladen el 26 de Mzo. de 2013
Could anybody upload some examples of modified tansig.m and +tansig folder? This would be very helpful for my project and for other people too. Thank You.
  1 comentario
Nn Sagita
Nn Sagita el 29 de Ag. de 2013
If you have some examples how to modify transfer function, please share for me. Thank you.

Iniciar sesión para comentar.

mladen
mladen el 29 de Mzo. de 2013
Thank you Bob. Nice trick with feedforwardnet.m (good for permanent use). I've managed to do this but some new questions arise:
  1. How to use param in apply(n,param) ? (more info-> matlabcentral/answers/686)?
  2. How to use different transfer functions within the same layer?
  3. My apply function looks something like this:
function A = apply(n,param)
%....
A=a1.*a2;
end
now I would like to use a1 and a2 to speedup the derivative computation in da_dn.m (this has already been done with tansig.m, but with the final value (A in my code))...is it possible?

Categorías

Más información sobre Sequence and Numeric Feature Data Workflows en Help Center y File Exchange.

Etiquetas

Productos

Community Treasure Hunt

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

Start Hunting!

Translated by