Abandoning the Dark Arts: New Directions in Efficient DNN Design
Kurt Keutzer
2019 Invited Talk
in
Workshop: EMC2: Energy Efficient Machine Learning and Cognitive Computing (5th edition)
in
Workshop: EMC2: Energy Efficient Machine Learning and Cognitive Computing (5th edition)
Abstract
Deep Neural Net models have provided the most accurate solutions to a very wide variety of problems in vision, language, and speech; however, the design, training, and optimization of efficient DNNs typically requires resorting to the “dark arts” of ad hoc methods and extensive hyperparameter tuning. In this talk we present our progress on abandoning these dark arts by using Differential Neural Architecture Search to guide the design of efficient DNNs and by using Hessian-based methods to guide the processes of training and quantizing those DNNs.
Chat is not available.
Successful Page Load