A Spline Theory of Deep Learning
Abstract
Deep learning has significantly advanced our ability to address a wide range of difficult machine learning and signal processing problems. Today’s machine learning landscape is dominated by deep (neural) networks (DNs), which are compositions of a large number of simple parameterized linear and nonlinear operators. An all-too-familiar story is that of plugging a deep network into an application as a black box, learning its parameter values using copious training data, and then significantly improving performance over classical task-specific approaches.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Sep 19, 2018
- Source ID
- FA95501810478
Entities
People
- Richard G. Baraniuk
Organizations
- Air Force Office of Scientific Research
- Rice University
- United States Air Force