Over fitting in Stacked Denoising Autoencoders

[Ahmed--Mohsen]

In the finetune phase, the whole dataset is used which will cause over fitting for the model... So, I think this can be solved by:

• divide the dataset into training, test & validation sets
• Or, using a k-fold cross validation

[thanasik]

Very true, I also think separating the data into different sets, as you said, is the approach to go.