search

albertbup / deep-belief-network

A Python implementation of Deep Belief Networks built upon NumPy and TensorFlow with scikit-learn compatibility
MIT License
481 stars 212 forks source link

Question regarding hidden_layers_structure #21

Closed eragonngo closed 7 years ago

eragonngo commented 7 years ago

Dear albertbup,

First of all, thank you so much for implementing DBN into Python with lots of example from logistic regression, linear regression. Also, I have a question with your sample code, which is: hidden_layers_structure = [256,256], does that mean this DBN has 2 hidden layers with 256 neurons in each hidden layer ? Because I believe a standard DBN usually has 3 hidden layers (with hidden layer 1 as RBM). Hope you can help with my confusion.

Thank you for your time,

Sincerely,

albertbup commented 7 years ago

Hey,

...does that mean this DBN has 2 hidden layers with 256 neurons in each hidden layer ?

Exactly.

Because I believe a standard DBN usually has 3 hidden layers (with hidden layer 1 as RBM)

DBN is just a composition of an arbitrary number of stacked RBM's, find out more here.

Best regards,