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

S7825 - Task-Based Model Learning and Optimization as a Neural Network Layer

Session Speakers
Session Description

We'll present the task-based model learning framework, a machine learning framework for optimizing models that are used within some larger decision-making process. Unlike traditional training methods, which typically minimize a simple loss function, the proposed system minimizes the full end-to-end cost of the decision-making process. To accomplish this, we developed a novel approach for differentiating through constrained optimization problems, allowing us to treat the entire prediction and decision-making pipeline as a single, highly-structured neural network. We have developed an efficient, open-source implementation of the method, making use of batch factorization methods available within the CUBLAS library.


Additional Session Information
All
Talk
Deep Learning and AI Energy Exploration Intelligent Machines and IoT
Energy / Oil & Gas General
25 minutes
Session Schedule