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
Proceedings ArticleDOI
Text Categorization Based on Boosting Association Rules
Yongwook Yoon,Gary Geunbae Lee +1 more
TL;DR: This work proposes a new approach in which a large number of association rules are generated and filtered using a new method which is equivalent to a deterministic Boosting algorithm, which effectively adapts to large-scale classification tasks such as text categorization.
Posted Content
Efficient Robust Proper Learning of Log-concave Distributions
TL;DR: This work gives the first computationally efficient algorithm for the robust proper learning of univariate log-concave distributions, which achieves the information-theoretically optimal sample size, runs in polynomial time, and is robust to model misspecification with nearly-optimal error guarantees.
Posted Content
Experimental learning of quantum states
Andrea Rocchetto,Andrea Rocchetto,Scott Aaronson,Simone Severini,Simone Severini,Gonzalo Carvacho,Davide Poderini,Iris Agresti,Marco Bentivegna,Fabio Sciarrino +9 more
TL;DR: In this paper, it was shown that quantum states can be approximately learned using only a linear number of measurements, in a probabilistic setting, in which the number of parameters describing a quantum state is linearly scaled with the quantum number of qubits.
Proceedings Article
Searching For Hidden Messages: Automatic Detection of Steganography
TL;DR: This work uses ML algorithms to distinguish clean and stego-bearing files, and shows that ML algorithms work in both content- and compression-based image formats, outperforming at least one current hand crafted steganalysis technique in the latter.
Proceedings ArticleDOI
A comparative study on model selection and multiple model fusion
TL;DR: It is argued that strong consistency only holds under large sample regime while soft model selection can still be better than choosing a single model with small sample size and the conditional model estimator (CME) has the best performance in selecting the correct model order and fusing multiple models for prediction and interpolation.