How to retrain existing and trained Neural Network without destroying trained content?

Question

Mirek Wilmer 2018-4-23

2
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/396721-how-to-retrain-existing-and-trained-neural-network-without-destroying-trained-content

评论： TROY TULLY 2021-4-9

Matlab train() function used for training the neural network initializes all weights and other internal parameters of the network at the beginning. I would like to take a trained network and train it further using new set of data without reinitializing and starting from scratch (destroying the trained net basically). How do I do it ? Is there a way to use existing train() function or is there some re-train() function or do I need to build my own custom solution ? The last option seems unlikely, given the amount of the existing Matlab code. Please advise, Thanks, Mirek Wilmer mirek.wilmer@gmail.com

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

manisha milani 2019-10-29

编辑：manisha milani 2019-10-29

在 MATLAB Online 中打开

y=net(x) % y is the trained output
mynet = net; 
save mynet;
load mynet;
test = mynet(new_data);

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Greg Heath 2018-8-7

4
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/396721-how-to-retrain-existing-and-trained-neural-network-without-destroying-trained-content#answer_331949

编辑：Greg Heath 2018-8-7

TRAIN initializes weights ONLY IF ALL weights are zero.

OTHERWISE

TRAIN will update weights with the new data.

Therefore old weights will be modified to fit the new data.

If the new data is unlike the old data, performance on the old data will be degraded.

In order to prevent "FORGETTING", a characteristic subset of the old data SHOULD BE MIXED with the new data for the retraining.

Hope this helps.

Thank you for formally accepting my answer

Greg

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Answer 2

Greg Heath 2018-8-3

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/396721-how-to-retrain-existing-and-trained-neural-network-without-destroying-trained-content#answer_331407

In order to preserve the dominant characteristics of the 1st dataset you must include that information while adapting to the new data. Therefore I always represent the 1st data set by a representative subset and add that to the new set.

I have been most successful when using Elliptic or Gaussian basis functions (with limited effective range) in the net.

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

TROY TULLY 2021-4-9

Hi Greg,

Do you know of a way to have a computer search through the training data to find a represntative subset?

请先登录，再进行评论。

Answer 3

KSSV 2018-4-23

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/396721-how-to-retrain-existing-and-trained-neural-network-without-destroying-trained-content#answer_316649

在 MATLAB Online 中打开

The function train gives out a structure variable net with all the information of training the inputs have under gone.

[net,tr] = train(net,.......)

If you don't clear your workspace, you can use the variable net for what you want. It will retain all the previous data.

[net,tr] = train(net,newdata.....)

4 个评论
显示 2更早的评论隐藏 2更早的评论

Gideon Prior 2018-8-7

That isnt the case unfortunately. Calls to 'train' reinitialize the weights, which is odd since there is a method 'init' already included in the toolbox. I dont know why the mathworks folks decided to not include an option to prevent initialization when 'train' is called.

Kinga Wilmer 2018-8-7

As a mater of fact, if the workspace is not cleared and the definition of net is not changed, then train() function does not destroy the existing weights. I did trace the whole process with a debugger step by step and confirmed it. Therefore you can re-use your trained net for further training. Mind you, the additional data may re-train your net, so if you want to retain the existing trained capacity, you need to keep statistically important sample representation of your previous training data in the new training dataset. Therefore only small incremental retraining steps make sense. Another way is to train number of separate networks and combine them into hierarchical model.

请先登录，再进行评论。