No
Yes
View More
View Less
Working...
Close
OK
Cancel
Confirm
System Message
Delete
Schedule
An unknown error has occurred and your request could not be completed. Please contact support.
Scheduled
Wait Listed
Personal Calendar
Speaking
Conference Event
Meeting
Interest
Schedule TBD
Conflict Found
This session is already scheduled at another time. Would you like to...
Loading...
Please enter a maximum of {0} characters.
Please enter a maximum of {0} words.
must be 50 characters or less.
must be 40 characters or less.
Session Summary
We were unable to load the map image.
This has not yet been assigned to a map.
Search Catalog
Reply
Replies ()
Search
New Post
Microblog
Microblog Thread
Post Reply
Post
Your session timed out.
This web page is not optimized for viewing on a mobile device. Visit this site in a desktop browser to access the full set of features.
2017 GTC San Jose

S7442 - Pruning Convolutional Neural Networks for Resource-Efficient Inference

Session Speakers
Session Description

We'll introduce a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. The approach is based on interleaving greedy criteria-based pruning with fine-tuning by backpropagation -- a computationally efficient procedure that maintains good generalization in the pruned network. We'll propose a new criterion based on Taylor expansion that approximates the change in the cost function induced by pruning network parameters. We'll focus on transfer learning, where large pretrained networks are adapted to specialized tasks. The proposed criterion demonstrates superior performance compared to other criteria, for example, the norm of kernel weights or feature map activation, for pruning large CNNs after adaptation to fine-grained classification tasks (Birds-200 and Flowers-102) relaying only on the first order gradient information. We'll also show that pruning can lead to more than 10x theoretical reduction in adapted 3D-convolutional filters.


Additional Session Information
All
Talk
Deep Learning and AI
Higher Education / Research Software
25 minutes
Session Schedule