The perceptron algorithm versus winnow: linear versus logarithmic mistake bounds when few input variables are relevant

This publication has 8 references indexed in Scilit:

• Exponentiated Gradient versus Gradient Descent for Linear Predictors
  Information and Computation, 1997
• On-line learning of linear functions
  computational complexity, 1995
• The statistical mechanics of learning a rule
  Reviews of Modern Physics, 1993
• Learnability and the Vapnik-Chervonenkis dimension
  Journal of the ACM, 1989
• Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm
  Machine Learning, 1988
• A theory of the learnable
  Communications of the ACM, 1984
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
  Theory of Probability and Its Applications, 1971
• The perceptron: A probabilistic model for information storage and organization in the brain.
  Psychological Review, 1958