← Back to papers
2015 COLT COLT 2015

Norm-Based Capacity Control in Neural Networks

Abstract

We investigate the capacity, convexity and characterization of a general family of norm-constrained feed-forward networks.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
🧭 Keyword Pioneer — feedforward network
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Behnam Neyshabur , Ryota Tomioka , Nathan Srebro

Topics

Machine Learning > Optimization & Theory > Learning Theory Deep Learning > Architectures > Neural Networks

Keywords

feedforward network capacity control neural network
Download PDF

Related papers

Open Problem: Restricted Eigenvalue Condition for Heavy Tailed Designs 2015
Open Problem: The Oracle Complexity of Smooth Convex Optimization in Nonstandard Settings 2015
Online Learning with Feedback Graphs: Beyond Bandits 2015
Learning Overcomplete Latent Variable Models through Tensor Methods 2015
Efficient Learning of Linear Separators under Bounded Noise 2015