conftrace_

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.

🧭 Keyword Pioneer - feed-forward network

🐣 Hot Topic Early Bird - feed-forward network

Authors

Behnam Neyshabur, Ryota Tomioka, Nathan Srebro

Topics

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

Keywords

feed-forward network capacity control neural network

More from COLT 2015

All COLT 2015 papers →

Correlation Clustering with Noisy Partial Information

Online Density Estimation of Bradley-Terry Models

First-order regret bounds for combinatorial semi-bandits

Cortical Learning via Prediction

Partitioning Well-Clustered Graphs: Spectral Clustering Works!

Batched Bandit Problems