Testing a Backpropagation Neural Network

1 Ansicht (letzte 30 Tage)
Zeeshan Ahmad Khan
Zeeshan Ahmad Khan am 10 Feb. 2019
Beantwortet: Miss Jenny am 1 Okt. 2019
I have developed a backpropagation Neural Network in Matlab. The script for training the Network works fine and predicted output follows the expected output.
The weights, biases, network architecture,inputs, targets from training network are stored in the .mat file. This .mat file is then loaded in the testing script and only the forward propagation part is implemented in the testing script to get the expected output.
However, the output from testing is not anywhere close to the expected output even though the training accuracy is quite high (more than 95% in each run).
Is it because the network is not being trained enough or Is it some problem with the code that needs debugging? Can someone tell the reason for it and any possible solutions to the problem.
Attached are the files used for training and testing.
Any leads would be appreciated.

Akzeptierte Antwort

Greg Heath
Greg Heath am 10 Feb. 2019
You are probably
OVERTRAINING AN OVERFIT NET
OVERFITTING: Using more unknown hidden nodes than number of training equations
OVERTRAINING:Training longer than is practical for a good solution.
I have written several zillion posts in both the NEWSGROUP and ANSWERS
Hope this helps
Thank you for formally accepting my answer
Greg
  1 Kommentar
Zeeshan Ahmad Khan
Zeeshan Ahmad Khan am 11 Feb. 2019
I have reduced the number of hidden nodes and have calculated the number of training equations and weights accroding to the following equation:
For a double hidden layer network,
Ntrneq = Ntrn*O
Nw = (I+1)*H1 + (H1+1)*H2+(H2+1)*O
However, regarding Overtraining, can you provide a lead on how to get rid of Overtraining.
I have already implemened L2 regularization in the script.
Any leads would be appreciated.

Melden Sie sich an, um zu kommentieren.

Weitere Antworten (1)

Miss Jenny
Miss Jenny am 1 Okt. 2019
Can someone tell me how to test the networks, i have training the dataset by using the pattern recognition apps in the toolbox. But i don't know how to proceed with testing the networks.

Kategorien

Mehr zu Get Started with Deep Learning Toolbox finden Sie in Help Center und File Exchange

Produkte

Community Treasure Hunt

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

Start Hunting!

Translated by