Modern Tools for Classification and Clustering
Abstract
The availability of massive datasets and the emergence of sophisticated algorithms have precipitated un-precedented success in machine learning. Academic and industry researchers, including Google and Face-book have unveiled state-of-the-art image, face, and speech recognition technologies that boast near-human accuracy. Each of these technologies however is the result of training a deep neural network on millions or billions of training samples, a volume of data available to data giants like Google or Facebook precisely due to their commercial scale. These striking results raise a critical issue of reducing the volume of training data required.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Sep 11, 2017
- Source ID
- FA95501710291
Entities
People
- Amit Singer
Organizations
- Air Force Office of Scientific Research
- Trustees of Princeton University
- United States Air Force