Recent developments in Deep Learning

Recently, I watched Hinton’s talk on recent developments in deep learning. Main points are as below:

1. Replace sigmoid function with rectified linear function: easily for training and test, plus efficient. 

2. Dropout training and test could improve accuracy significantly, becasue this is basicly aggregating different highly regularized deep learning model by a geometric mean.

This might be a standard recipe for current deep learning. Based on this recipe, several students of his have won many Kaggle chagllenge. 


About zhanxing

Ph.D student in Machine Learning, University of Edinburgh, UK.
This entry was posted in Life and tagged . Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your 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 )


Connecting to %s