How to use a custom transfer function in neural net training

Bob
2012 12 9
6 个回答
回答已采纳
更新时间：2023 2 23
4 次查看（30 天）

1 个投票

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.

请先登录，再回答此问题。

 采纳的回答

Greg Heath
Greg Heath 2012-12-9
编辑：Walter Roberson 2017-8-13

0 个投票

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 个评论
显示 -1更早的评论 隐藏 -1更早的评论

Greg Heath
Greg Heath 2012-12-9
编辑：DGM 2023-2-23
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

请先登录，再进行评论。

更多回答（5 个）

Bob
Bob 2013-3-27

7 个投票

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 个评论
显示 2更早的评论 隐藏 2更早的评论

Nn Sagita
Nn Sagita 2013-8-29
Bob, I modified purelin transfer function, called 'mtf'. I saved in my working directory. I trained neural network and got outputs. But I got some messages too, like this:
Exception in thread "AWT-EventQueue-0" java.lang.NullPointerException at com.mathworks.toolbox.nnet.v6.diagram.nnTransfer.paint(nnTransfer.java:35) at com.mathworks.toolbox.nnet.v6.image.nnOffsetImage.paint(nnOffsetImage.java:49) at ....
Could you help me, what should I do?
kelvina
kelvina 2014-2-15
thanks bob, it helps me
but we can directly do this by coping file 'template transfer' from :C:\Program Files (x86)\MATLAB\R2010a\toolbox\nnet\nnet\nncustom
and just replace its function :a = apply_transfer(n,fp) by your function and then save this file in your working directory. it will work.
Mayank Gupta
Mayank Gupta 2016-5-4
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 2018-7-16
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

请先登录，再进行评论。

Bob
Bob 2012-12-10

0 个投票

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 2012-12-11
编辑：DGM 2023-2-23

0 个投票

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 2013-3-26

0 个投票

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 个评论
显示 -1更早的评论 隐藏 -1更早的评论

Nn Sagita
Nn Sagita 2013-8-29
If you have some examples how to modify transfer function, please share for me. Thank you.

请先登录，再进行评论。

mladen
mladen 2013-3-29

0 个投票

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?

类别

在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

产品

标签

Community Treasure Hunt

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

Start Hunting!

Translated by