Neural network validation checks net.TrainParam.max_fail <- is a bigger or a smaller number better?

43 次查看（过去 30 天）
NightStalker
NightStalker 2021-9-16
回答： pathakunta 2024-1-26
While trying to improve my neural network I wondered, whether I should increase or decrease
TrainParam.max_fail
(default value is 6)
This documentary (https://de.mathworks.com/help/deeplearning/ref/trainlm.html) says:
Training stops when any of these conditions occurs:
  • "Validation performance has increased more than max_fail times since the last time it decreased (when using validation)."
which I interpret as: if validation error decreases more than 6 times -> early stopping
This documentary (https://de.mathworks.com/help/deeplearning/ug/improve-neural-network-generalization-and-avoid-overfitting.html) says:
When the validation error increases for a specified number of iterations (net.trainParam.max_fail), the training is stopped, and the
weights and biases at the minimum of the validation error are returned.
which I interpret as: if validation error increases more than 6 times -> early stopping
So what is the purpose of the net.TrainParam.max_fail?
____________________________________________________________________________________
Second question in the same post:
When my Trainratio/Validationratio/Testratio is 70/25/5.
After how many Train-epochs is there an Validation-Epoch?
Thank you very much in advance!

请先登录，再回答此问题。

采纳的回答

Anshika Chaurasia
Anshika Chaurasia 2021-10-8
Hi,
1. Training stops when any of these conditions occurs:
  • "Validation performance has increased more than max_fail times since the last time it decreased (when using validation)."
In above lines, "Validation Performance" means validation error. Hence, the interpretation of above line will be:
if validation error increases more than 6 times -> early stopping
To understand the terminology refer to following documents:
Calculate network performance - MATLAB perform (mathworks.com)
https://www.mathworks.com/help/deeplearning/ug/neural-network-object-properties.html#bss4hk6-52
2. After each training epoch validation will occur. Or, in an epoch first training will be done then validation.
  1 个评论
NightStalker
NightStalker 2021-10-21
编辑：NightStalker 2021-10-21
Hi Anshika Chaurasia,
this was the very solution to my first question. Thank you!
Your answer to my second question lead to more questions, which I really hope you can answer me:
2.a) What will happen, if the testset has 1000 samples but the validationset only 500? will the validation-procedures be evenly distributed over the test-procedures or will some validation samples be used more than 1 time and force the validation-procedure after every test-procedure?
2.b) After one test-procedure, how does MATLAB pick/choose the sample within the validationset to validate this test-procedure?
Thanks in advance!

请先登录，再进行评论。

更多回答（3 个）

pathakunta
pathakunta 2024-1-26
1. Training stops when any of these conditions occurs: "Validation performance has increased more than max_fail times since the last time it decreased (when using validation)." In above lines, "Validation Performance" means validation error. Hence, the interpretation of above line will be: if validation error increases more than 6 times -> early stopping To understand the terminology refer to following documents: Calculate network performance - MATLAB perform (mathworks.com) https://www.mathworks.com/help/deeplearning/ug/neural-network-object-properties.html#bss4hk6-52 2. After each training epoch validation will occur. Or, in an epoch first training will be done then validation.
pathakunta
pathakunta 2024-1-26
1. Training stops when any of these conditions occurs: "Validation performance has increased more than max_fail times since the last time it decreased (when using validation)." In above lines, "Validation Performance" means validation error. Hence, the interpretation of above line will be: if validation error increases more than 6 times -> early stopping To understand the terminology refer to following documents: Calculate network performance - MATLAB perform (mathworks.com) https://www.mathworks.com/help/deeplearning/ug/neural-network-object-properties.html#bss4hk6-52 2. After each training epoch validation will occur. Or, in an epoch first training will be done then validation.
pathakunta
pathakunta 2024-1-26
1. Training stops when any of these conditions occurs: "Validation performance has increased more than max_fail times since the last time it decreased (when using validation)." In above lines, "Validation Performance" means validation error. Hence, the interpretation of above line will be: if validation error increases more than 6 times -> early stopping To understand the terminology refer to following documents: Calculate network performance - MATLAB perform (mathworks.com) https://www.mathworks.com/help/deeplearning/ug/neural-network-object-properties.html#bss4hk6-52 2. After each training epoch validation will occur. Or, in an epoch first training will be done then validation.

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

产品

Community Treasure Hunt

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

Start Hunting!

Translated by