How can I continue training with additional data to an already existed neural network?
3 views (last 30 days)
Show older comments
Lamesginew
on 9 Oct 2014
Edited: Roberto de Freitas Cabral
on 30 Aug 2018
I have a trained neural network with some data set, let A. That is, the network is trained on data set A. Later on, I want to train this network which is trained on data set A with some additional data set, let B. I think, making together data set A and B, and then training the network is possible. But, what I want is not training for the merged data set, rather continue training on the existed trained network for data set B only. Any help for this... contact me via lame2002@gmail.com. Thanks,
0 Comments
Accepted Answer
Greg Heath
on 10 Oct 2014
In general, this technique will not work if you want to preserve good performance on A.
If you don't want to use all of A, use a subset that exemplifies the basic characteristics of A.
There is a huge history of NN forgetting. Don't waste your time with your original idea.
Spend your time thinking about how to find that characterization subset. Unsupervised clustering of A is one idea. Then use the A cluster centers with B.
Hope this helps.
Thank you for formally accepting my answer
Greg
0 Comments
More Answers (1)
Roberto de Freitas Cabral
on 30 Aug 2018
Edited: Roberto de Freitas Cabral
on 30 Aug 2018
Although I'm new to neural networks and MATLAB, I had the same question recently.
Searching the web, I've found an interesting link that certainly has to do with your question: https://www.mathworks.com/help/nnet/ug/neural-network-training-concepts.html
I hope it helps.
0 Comments
See Also
Categories
Find more on Image Data Workflows 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!