Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Optimal Linear Combination of Classifiers

Mar 01, 2021
Georgi Nalbantov, Svetoslav Ivanov

The question of whether to use one classifier or a combination of classifiers is a central topic in Machine Learning. We propose here a method for finding an optimal linear combination of classifiers derived from a bias-variance framework for the classification task.

* 14 pages, 7 figures 

  Access Paper or Ask Questions

Notes on Electronic Lexicography

Jul 09, 2011
Yavor Parvanov

These notes are a continuation of topics covered by V. Selegej in his article "Electronic Dictionaries and Computational lexicography". How can an electronic dictionary have as its object the description of closely related languages? Obviously, such a question allows multiple answers.

* 8 pages, 1 figure 

  Access Paper or Ask Questions

"I'm sorry Dave, I'm afraid I can't do that": Linguistics, Statistics, and Natural Language Processing circa 2001

Apr 21, 2003
Lillian Lee

A brief, general-audience overview of the history of natural language processing, focusing on data-driven approaches.Topics include "Ambiguity and language analysis", "Firth things first", "A 'C' change", and "The empiricists strike back".

* In "Computer Science: Reflections on the Field, Reflections from the Field" (report of the National Academies' Study on the Fundamentals of Computer Science), pp. 111--118, 2004 
* To appear, National Research Council study on the Fundamentals of Computer Science. 7 pages 

  Access Paper or Ask Questions

Defense Against the Dark Arts: An overview of adversarial example security research and future research directions

Jun 11, 2018
Ian Goodfellow

This article presents a summary of a keynote lecture at the Deep Learning Security workshop at IEEE Security and Privacy 2018. This lecture summarizes the state of the art in defenses against adversarial examples and provides recommendations for future research directions on this topic.

  Access Paper or Ask Questions

Machine Learning and Applied Linguistics

Mar 24, 2018
Sowmya Vajjala

This entry introduces the topic of machine learning and provides an overview of its relevance for applied linguistics and language learning. The discussion will focus on giving an introduction to the methods and applications of machine learning in applied linguistics, and will provide references for further study.

* Pre-print version of the article that is accepted for publication in "Encyclopedia of Applied Linguistics" 

  Access Paper or Ask Questions

Visual Transfer Learning: Informal Introduction and Literature Overview

Nov 06, 2012
Erik Rodner

Transfer learning techniques are important to handle small training sets and to allow for quick generalization even from only a few examples. The following paper is the introduction as well as the literature overview part of my thesis related to the topic of transfer learning for visual recognition problems.

* part of my PhD thesis 

  Access Paper or Ask Questions

Building of Networks of Natural Hierarchies of Terms Based on Analysis of Texts Corpora

May 23, 2014
Dmitry Lande

The technique of building of networks of hierarchies of terms based on the analysis of chosen text corpora is offered. The technique is based on the methodology of horizontal visibility graphs. Constructed and investigated language network, formed on the basis of electronic preprints arXiv on topics of information retrieval.

* 5 pages, 5 figures 

  Access Paper or Ask Questions

Foundations of Probability Theory for AI - The Application of Algorithmic Probability to Problems in Artificial Intelligence

Mar 27, 2013
Ray Solomonoff

This paper covers two topics: first an introduction to Algorithmic Complexity Theory: how it defines probability, some of its characteristic properties and past successful applications. Second, we apply it to problems in A.I. - where it promises to give near optimum search procedures for two very broad classes of problems.

* Appears in Proceedings of the First Conference on Uncertainty in Artificial Intelligence (UAI1985) 

  Access Paper or Ask Questions

Representation Learning for Natural Language Processing

Feb 07, 2021
Zhiyuan Liu, Yankai Lin, Maosong Sun

This book aims to review and present the recent advances of distributed representation learning for NLP, including why representation learning can improve NLP, how representation learning takes part in various important topics of NLP, and what challenges are still not well addressed by distributed representation.

* Published in Springer 

  Access Paper or Ask Questions

Collective Adaptive Systems: Challenges Beyond Evolvability

Aug 29, 2011
Serge Kernbach, Thomas Schmickl, Jon Timmis

This position paper overviews several challenges of collective adaptive systems, which are beyond the research objectives of current top-projects in ICT, and especially in FET, initiatives. The attention is paid not only to challenges and new research topics, but also to their impact and potential breakthroughs in information and communication technologies.

* Workshop "Fundamentals of Collective Adaptive Systems", European Commission, 3-4 November, 2009, Brussels 

  Access Paper or Ask Questions