Open AccessBook
An Introduction to Computational Learning Theory
Michael Kearns,Umesh Vazirani +1 more
Reads0
Chats0
TLDR
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata is described.Abstract:
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata by experimentation appendix - some tools for probabilistic analysis.read more
Citations
More filters
Journal Article
Algorithms and hardness results for parallel large margin learning
Phil Long,Rocco A. Servedio +1 more
TL;DR: In this article, the authors consider the problem of learning an unknown large-margin halfspace in the context of parallel computation, and give both positive and negative results, including a parallel algorithm based on Nesterov's that performs gradient descent with a momentum term.
Book ChapterDOI
Integer Linear Programming for Pattern Set Mining; with an Application to Tiling
Abdelkader Ouali,Abdelkader Ouali,Albrecht Zimmermann,Samir Loudni,Yahia Lebbah,Bruno Crémilleux,Patrice Boizumault,Lakhdar Loukil +7 more
TL;DR: This paper formulate the pattern set mining problem as an optimization task, ensuring that the produced solution is the best one from the entire search space, and proposes a method based on integer linear programming that is exhaustive, declarative and optimal.
Coupling techniques for dense surface registration: a continuous-discrete approach
TL;DR: This thesis achieves dense, accurate tracking results, which is demonstrated through a series of dense, anisometric 3D surface tracking experiments, and takes advantage of conformal mapping based method which derives a closed-form solution to dense surface matching.
Proceedings Article
Connecting human and machine learning via probabilistic models of cognition
TL;DR: This work will talk about how probabilistic models can be used to identify the assumptions of learners, learn at different levels of abstraction, and link the inductive biases of individuals to cultural universals.
Journal ArticleDOI
Statistical Active Learning Algorithms for Noise Tolerance and Differential Privacy
TL;DR: In this article, the authors describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially private, based on the powerful statistical query framework of Kearns (JACM 45(6):983---1006, 1998).