Ajalon: Simplifying the Authoring of Wearable Cognitive Assistants

no code implementations • 14 Jan 2021 • Truong An Pham, Junjue Wang, Yu Xiao, Padmanabhan Pillai, Roger Iyengar, Roberta Klatzky, Mahadev Satyanarayanan

Wearable Cognitive Assistance (WCA) amplifies human cognition in real time through a wearable device and low-latency wireless access to edge computing infrastructure.

Edge-computing Human-Computer Interaction

Accelerating Deep Learning by Focusing on the Biggest Losers

2 code implementations • 2 Oct 2019 • Angela H. Jiang, Daniel L. -K. Wong, Giulio Zhou, David G. Andersen, Jeffrey Dean, Gregory R. Ganger, Gauri Joshi, Michael Kaminksy, Michael Kozuch, Zachary C. Lipton, Padmanabhan Pillai

This paper introduces Selective-Backprop, a technique that accelerates the training of deep neural networks (DNNs) by prioritizing examples with high loss at each iteration.