Noisy results from Neural Network

2014 8 10
2 个回答
回答已采纳
更新时间：2014 8 21
2 次查看（30 天）

0 个投票

I've trained a feed-forward neural network with 4 inputs and 2 targets with 10000 sample data. When I use this network for testing on a set of data, the average of data seems acceptable, but it is very noisy (see attached figure). Any suggestion to resolve this issue? I have tried many different layer and neuron numbers, as well as training methods, but no major improvement.

请先登录，再回答此问题。

 采纳的回答

Greg Heath
Greg Heath 2014-8-10

2 个投票

Try preprocessing with a lowpass filter.
The cheapest one I can think of is
x(i) = mean([x0(i-1),x0(i),x0(i+1)]) % 3-point moving average
I don't necessarily recommend it, it is just an example. Better to find a good LPF reference.
Hope this helps.
Thank you for formally accepting my answer
Greg

8 个评论
显示 6更早的评论 隐藏 6更早的评论

Sam136
Sam136 2014-8-10
Thanks for your answer Greg. Is there any way to get noise-free results from the NN itself without using lowpass filter. As I am new in NN area, I have no idea if this noisy result is a normal thing or not. I haven't seen this issue in many examples that I've reviewed.
Image Analyst
Image Analyst 2014-8-10
Or you can do Greg's method without a loop doing
movingAverageX = conv(x, [1,1,1]/3, 'same');
For a little less smoothing you can use sgolayfilt() (in the Signal Processing Toolbox) which uses polynomials of higher order than 1 (which is what a moving average is).
Greg Heath
Greg Heath 2014-8-12
In order to understand noisy results, you have to first analyze the noise of the input and target used in training.
If the training data is noiseless, then I would not expect the output from noisy nontraining input data to be noise free.
If you want the net to be robust w.r.t. noise you can either filter the data before inputting or train the net with noisy inputs and smooth outputs.
I am assuming you have a static net with no feedback or delays.
Greg
Sam136
Sam136 2014-8-18
Actually,both set of data (training and testing) are noise-free, but the response is noisy. I use static net. Do you think that it is the problem?
Greg Heath
Greg Heath 2014-8-19
If the data is static why not just sort the data with respect to the input value?
Sam136
Sam136 2014-8-19
Thanks Greg for your comment. Can you explain more about this.
Greg Heath
Greg Heath 2014-8-19
Sorry, my response assumed the input data was one-dimensional.
I think you can better understand your results if you do the following for each input
[sortx1 ind1] = sort(input(1,:));
figure, hold on plot(sortx1,target(ind1),'k--') plot(sortx1,output(ind1),'b')
Hope this helps,
Greg
Greg Heath
Greg Heath 2014-8-19
It doesn't appear to me that the output is significantly more noisy than the target.
Maybe you can see it better with other plotting options or plotting error (target-output).

请先登录，再进行评论。

更多回答（1 个）

Sam136
Sam136 2014-8-20
编辑：Sam136 2014-8-20

0 个投票

I changed my net to dynamic(narxnet) with zero delay for input and 1:2 delay for feedback, but I still have the problem. Below figures show NN response to the input data (same data that I used for training the network).

2 个评论
显示 无 隐藏 无

Greg Heath
Greg Heath 2014-8-20
If you are going to switch to narxnet. See my posts on how to choose delays
greg nncorr
how to choose number of hidden nodes
greg Hub
and how to normalize results
greg NMSE
greg R2
greg R2a
Sam136
Sam136 2014-8-21
编辑：Sam136 2014-8-21
Thanks Greg. The network worked, and the results are pretty good. I have a question though. I have a difficulty to use the trained network (narxnet) for new set of input data. I get dimension error and it seems that I should include the target values. However, there is no target values when we want to use the network. Can you help me in this regard?

请先登录，再进行评论。

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