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
Book
On the Physical Security of Physically Unclonable Functions
TL;DR: This work investigates the susceptibility of Intrinsic PUF implementations on reconfigurable hardware to optical semi-invasive attacks from the chip backside, and reviews the potential and already realized countermeasures, which can remedy the security-related shortcomings of the PUFs and make them resistant to optical side-channel and optical fault attacks.
Proceedings ArticleDOI
Experimental design of time series data for learning from dynamic Bayesian networks.
C. David Page,Irene M. Ong +1 more
TL;DR: A theoretical analysis on the ability of DBNs without hidden variables to learn from proteomic time series data reveals that under a reasonable set of assumptions a fixed budget is better spent on collecting many short time seriesData than on a few long time seriesdata.
BookDOI
Verification, Model Checking, and Abstract Interpretation
Isil Dillig,Jens Palsberg +1 more
TL;DR: This talk considers compositionality for Concurrent Program Proofs in the context of knowledge representation, and some examples show how this can be improved on the basis of explicit specification and examples.
Dissertation
Parameter Tuning Using Gaussian Processes
TL;DR: Through the analysis of experimental results obtained on datasets from the UCI repository, the GPO algorithm yields competitive performance compared with a brute-force approach, while exhibiting a distinct advantage in terms of training time and number of cross-validation runs.
Dissertation
Sentiment Analysis in Financial News
TL;DR: This work decided to develop a system that can analyse news in the financial domain by exploiting several publicly available lexicons and classified the news as positive, negative or neutral, and obtained enriched lexicons.