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
DissertationDOI
Stance Detection and Analysis in Social Media
TL;DR: This research explores the task of automatically determining from the text whether the author of the text is in favor of, against, or neutral towards a proposition or target, and proposed a novel framework for joint learning of stance and reasons behind it based on topic modeling.
Proceedings ArticleDOI
Simulation-based target test generation techniques for improving the robustness of a software-based-self-test methodology
TL;DR: The potential of using target test program generation (TTPG) to supplement the RTPG method for achieving high fault coverage in software-based self-test of a RISC pipelined microprocessor design is investigated.
Active automata learning for real-life applications
TL;DR: This dissertation is a result of having being challenged, motivated, and supported in a truly unique environment, created by the persons that gathered at the Chair of Programming Systems to create and cooperate.
Journal ArticleDOI
Is there a role for statistics in artificial intelligence
Sarah Friedrich,Gerd Antes,Sigrid Behr,Harald Binder,Werner Brannath,Florian Dumpert,Katja Ickstadt,Hans A. Kestler,Johannes Lederer,Heinz Leitgöb,Markus Pauly,Ansgar Steland,Adalbert F. X. Wilhelm,Tim Friede +13 more
TL;DR: In this paper, the authors highlight the relevance of statistical methodology in the context of AI development and discuss contributions of statistics to the field of artificial intelligence concerning methodological development, planning and design of studies, assessment of data quality and data collection, differentiation of causality and associations and assessment of uncertainty in results.
Posted Content
Learning without Interaction Requires Separation.
Amit Daniely,Vitaly Feldman +1 more
TL;DR: It is shown that a similar separation holds for any class with large margin complexity that is closed under negation, without assumptions on the distribution, and that non-interactive SQ algorithms can only learn function classes of low margin complexity.