I've tried to follow the example provided at mathworks for training a deep sparse autoencoder (4 layers), so i pre-trained the autoencoders separately and then stacked then into a deep network. When i try to finetune this network though, via the train(deepnet, InputDataset) instruction, the training stops instantly and i receive a "performance goals met" message. Is there a way to train and finetune a deep autoencoder network in an unsupervised manner in Matlab (no labels provided)?
Asked
Active
Viewed 412 times
1 Answers
0
Have you set the "MSE" goal? Secondly, for fine tuning of network use a conventional back-propagation algorithm in supervised fashion.

Nathan Tuggy
- 2,237
- 27
- 30
- 38

Case Msee
- 405
- 5
- 17
-
Stack Overflow is not a site to share contact info or send private messages. Either share answers with everyone, or don't post. – Nathan Tuggy Apr 21 '17 at 02:33
-
I still don't know the answer, so nothing to share really. I ended up using different approaches (manual networks and layers). – L.Thanos May 22 '17 at 10:31