Quiz for Jan 31 Zhao Yangyang

We know that the deep learning is very difficult to train. What is the difficulties ? Explicitly: if we apply the SGD algorithms and tuning the hyper-parameters with the techniques presented in the paper, can we train a ANN with many hidden layer ? If not, where is the problem?

Advertisements

0 Responses to “Quiz for Jan 31 Zhao Yangyang”



  1. Leave a Comment

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

w

Connecting to %s





%d bloggers like this: