Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Changing Model Behavior at Test-time Using Reinforcement Learning
Augustus Odena, Dieterich Lawson, Christopher Olah
Feb 17, 2017 (modified: Feb 17, 2017)ICLR 2017 workshop submissionreaders: everyone
Abstract:Machine learning models are often used at test-time subject to constraints and trade-offs not present
at training-time. For example, a computer vision model operating on an embedded device may need to perform
real-time inference, or a translation model operating on a cell phone may wish to bound its average
compute time in order to be power-efficient. In this work we describe a mixture-of-experts model and show how to change its test-time resource-usage on a per-input basis using reinforcement learning. We test our method on a small MNIST-based example.
TL;DR:We describe a method to change model behavior at test-time on a per-input basis using reinforcement learning in a mixture-of-experts framework.
Keywords:Reinforcement Learning, Deep learning
Enter your feedback below and we'll get back to you as soon as possible.