What is the error histogram in neural network matlab?

109 views (last 30 days)
I asked yesterday, but I don't understand. because I used neural network matlab tool first time
So I ask you again
1. error values don't have to minus value??
2. What is the y axis? is it the number of traning, validation and test data set?
3. why the highest bar exist? is it mean highst bar has 0.001502 error values?
4. what is zero error? I don't understand zero error line means. it means 0? it means distribution which bar close 0?
Is it best performance??? what does mean in this graph??
I'm sorry for many questions.. Thank you in advance.
  2 Comments
Aasma aslam
Aasma aslam on 3 Apr 2021
how I can get data for this error histogram? my FFNN is creating an error histogram automatically? How i can get the data that is used to plot this histogram?
imene. B
imene. B on 21 Sep 2022
if you're using the neural networks time series app in matlab it's generated automatically

Sign in to comment.

Answers (3)

Sourav Bairagya
Sourav Bairagya on 10 Dec 2019
Error histogram is the histogram of the errors between target values and predicted values after training a feedforward neural network. As these error values indicates how predicted values are differing from the target values, hence these can be negative.
Bins are the number of vertical bars you are observing on the graph. The total error range is divided into 30 smaller bins here.
Y-axis represents the number of samples from your dataset, which lies in a particular bin. For example, at the mid of your plot, you have a bin corresponding to the error of 0.001502 and the height of that bin for training dataset lies below but near to 150 and validation and test dataset lies between 150 and 200. It means that many samples samples from you different datasets have an error lies in that following range.
Zero error line corresponding to the zero error value on the error axis (i.e. X-axis). In this case zero error point falls under the bin with centre 0.001502.
To get more details you can leverage this link:
  1 Comment
Aasma aslam
Aasma aslam on 19 Aug 2022
Edited: Aasma aslam on 19 Aug 2022
Thank you very much for detail answer. Can you plz tell me accuracy of our results in percentage? from above histogram? I mean how i can tell the reviewers that our rests are ??? percent good?

Sign in to comment.


usha chintalapati
usha chintalapati on 15 May 2020
Can you please explain this plot?
  1 Comment
Mohit Nair
Mohit Nair on 13 May 2021
Error histogram is the histogram of the errors between target values and predicted values after training a feedforward neural network. As these error values indicates how predicted values are differing from the target values, hence these can be negative.
Bins are the number of vertical bars you are observing on the graph. The total error range is divided into 20 smaller bins here.
Y-axis represents the number of samples from your dataset, which lies in a particular bin. For example, at the mid of your plot, you have a bin corresponding to the error of -0.04225 to 0.04225 and the height of that bin for training dataset lies below but near to 40 and validation and test dataset lies between 50 and 60. It means that many samples samples from you different datasets have an error lies in that following range.
Zero error line corresponding to the zero error value on the error axis (i.e. X-axis). In this case zero error point falls under the bin with centre 0.04225.

Sign in to comment.


Abhilash Singh
Abhilash Singh on 20 Feb 2022
In addition to the above explanation, the readers may also visit the following article to know how to interpret the error histogram (https://www.mdpi.com/1424-8220/22/3/1070).
  1 Comment
Deepthi Deepthi
Deepthi Deepthi on 9 Mar 2022
How to plot the error histogram for a classification problem?
In a multiclass classification problem the outputs are labelled as different classes For eg: class1: 1 0 0 0,
class2: 0 1 0 0, class3: 0 0 1 0, class4: 0 0 1 0 etc. (or sometimes it is labelled as 1,2,3,4....for each classes).
From this how to calculate the error function. Is there any solution or is it valid for a classification problem?

Sign in to comment.

Categories

Find more on Data Distribution Plots in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!