2010
NeurIPS
NeurIPS 2010
On Herding and the Perceptron Cycling Theorem
Abstract
The paper develops a connection between traditional perceptron algorithms and recently introduced herding algorithms. It is shown that both algorithms can be viewed as an application of the perceptron cycling theorem. This connection strengthens some herding results and suggests new (supervised) herding algorithms that, like CRFs or discriminative RBMs, make predictions by conditioning on the input attributes. We develop and investigate variants of conditional herding, and show that conditional herding leads to practical algorithms that perform better than or on par with related classifiers such as the voted perceptron and the discriminative RBM.
📈
Trend Setter
- Meta-Learning
🐣
Hot Topic Early Bird
- neural network
Authors
Topics
Machine Learning > Core Methods > Classification
Machine Learning > Learning Types > Self-Supervised Learning
Machine Learning > Optimization & Theory > Learning Theory
Machine Learning > Optimization & Theory > Optimization
Deep Learning > Architectures > Neural Networks
Machine Learning > Learning Paradigms > Meta-Learning
Machine Learning > Learning Types > Supervised Learning
Machine Learning > Core Methods > Neural Networks
Machine Learning > Bayesian & Probabilistic > Conditional Random Fields