(Copy of my question)

I understand why deep generative models like DBN ( deep belief nets ) or DBM ( deep boltzmann machines ) are able to capture underlying structures in data and use it for various tasks ( classification, regression, multimodal representations etc ...).

But for the classification tasks like in Learning deep generative models, I was wondering why the network is fine-tuned on labeled-data like a feed-forward network and why only the last hidden layer is used for classification ?

During the fine-tuning and since we are updating the weights for a classification task ( not the same goal as the generative task ), could the network loose some of its ability to regenerate proper data ? ( and thus to be used for different classification tasks ? )

Instead of using only the last layer, could it be possible to use a partition of the hidden units of different layers to perform the classifications task and without modifying the weights ? For example, by taking a sub-set of hidden units of the last two layers ( sub-set of abstract representations ) and using a simple classifier like an SVM ?

Thank you in advance !