• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Advanced Search Include Citations

Tools

Sorted by:
Try your query at:
Semantic Scholar Scholar Academic
Google Bing DBLP
Results 1 - 10 of 1,728
Next 10 →

CAPTCHA: Using Hard AI Problems for Security

by Luis von Ahn, Manuel Blum, Nicholas J. Hopper, John Langford - IN PROCEEDINGS OF EUROCRYPT , 2003
"... We introduce captcha, an automated test that humans can pass, but current computer programs can't pass: any program that has high success over a captcha can be used to solve an unsolved Artificial Intelligence (AI) problem. We provide several novel constructions of captchas. Since captchas ..."
Abstract - Cited by 331 (4 self) - Add to MetaCart
have many applications in practical security, our approach introduces a new class of hard problems that can be exploited for security purposes. Much like research in cryptography has had a positive impact on algorithms for factoring and discrete log, we hope that the use of hard AI problems

Addressing the Curse of Imbalanced Training Sets: One-Sided Selection

by Miroslav Kubat, Stan Matwin - In Proceedings of the Fourteenth International Conference on Machine Learning , 1997
"... Adding examples of the majority class to the training set can have a detrimental effect on the learner's behavior: noisy or otherwise unreliable examples from the majority class can overwhelm the minority class. The paper discusses criteria to evaluate the utility of classifiers induced f ..."
Abstract - Cited by 234 (1 self) - Add to MetaCart
[(x; c(x)], where x is a vector of attribute values and c(x) is the corresponding concept label. For simplicity, we consider only problems where c(x) is either positive or negative, and all attributes are continuous. Since Fisher (1936), this task has received plenty of attention from statisticians

NATO STO Centre for Maritime Research and Experimentation

by Fotios Katsilieris, La Spezia Italy, Paolo Braca
"... Detection of malicious AIS position spoofing by exploiting radar information ..."
Abstract - Add to MetaCart
Detection of malicious AIS position spoofing by exploiting radar information

Planning under continuous time and resource uncertainty: A challenge for AI

by John Bresina, Nicolas Meuleauy, Sailesh Ramakrishnan, David Smith, Rich Washingtonx - In Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence , 2002
"... yQSS Group Inc. zQSS Group Inc. xRIACS experiment is assigned a scientific value). Different ob-servations and experiments take differing amounts of time and consume differing amounts of power and data storage.There are, in general, a number of constraints that govern the rovers activities: ffl Ther ..."
Abstract - Cited by 120 (20 self) - Add to MetaCart
There are time, power, data storage, and posi-tioning constraints for performing different activities. Time constraints often result from illuminationrequirement--that is, experiments may require that a target rock or sample be illuminated with a certain in-tensity, or from a certain angle.

The structure of complete stable minimal surfaces in 3-manifolds of non-negative scalar curvature.

by Doris Fischer-Colbrie , Richard Schoen - Comm. Pure Appli. Math. , 1980
"... The purpose of this paper is to study minimal surfaces in three-dimensional manifolds which, on each compact set, minimize area up to second order. If M is a minimal surface in a Riemannian three-manifold N, then the condition that M be stable is expressed analytically by the requirement that o n a ..."
Abstract - Cited by 192 (1 self) - Add to MetaCart
any compact domain of M, the first eigenvalue of the operator A+Ric(v)+(AI* be positive. Here Ric (v) is the Ricci curvature of N in the normal direction to M and (A)' is the square of the length of the second fundamental form of M. In the case that N is the flat R3, we prove that any complcte

The Basic AI Drives

by Stephen M. Omohundro - In Proceedings of the First Conference on Artificial General Intelligence
"... Abstract. One might imagine that AI systems with harmless goals will be harmless. This paper instead shows that intelligent systems will need to be carefully designed to prevent them from behaving in harmful ways. We identify a number of “drives” that will appear in sufficiently advanced AI systems ..."
Abstract - Cited by 40 (0 self) - Add to MetaCart
Abstract. One might imagine that AI systems with harmless goals will be harmless. This paper instead shows that intelligent systems will need to be carefully designed to prevent them from behaving in harmful ways. We identify a number of “drives” that will appear in sufficiently advanced AI systems

Worldwide AI

by Ramon Lopez De Mantaras
"... Barcelona. IIIA grew out of an AI research group at the Cen-ter for Advanced Studies in Blanes (Spain) that started AI research in 1985. On average IIIA has had about 50 members per year during the last 12 years with a peak of almost 80 members in 2012. In total around 200 different people, includin ..."
Abstract - Add to MetaCart
research center, belonging to the Spanish National Research Council (CSIC), dedicated to AI research. We focus our activities on a few well-defined subdomains of artificial intelligence, positively avoiding dispersion and keeping a good balance between basic research and applications, and paying particular

Building up AI Resources as an AI Testbed

by Wolfgang Nejdl, Hadhami Dhraief, Boris Wolf , 2001
"... In this position paper, we will first give a short overview of our background and then propose to build up AI resources both as a service to the AI community but also as a testbed for AI techniques. ..."
Abstract - Add to MetaCart
In this position paper, we will first give a short overview of our background and then propose to build up AI resources both as a service to the AI community but also as a testbed for AI techniques.

Usable AI: Experience and reflections

by Krzysztof Z. Gajos, Daniel S. Weld - In Workshop on Usable Artificial Intelligence (at CHI’08 , 2008
"... We believe that AI has much to offer HCI, in particular allowing for the quick construction of personalized and personalizable interfaces. In this position paper, we report on our experience from four recent ..."
Abstract - Cited by 4 (3 self) - Add to MetaCart
We believe that AI has much to offer HCI, in particular allowing for the quick construction of personalized and personalizable interfaces. In this position paper, we report on our experience from four recent

i=1 ai and

by unknown authors
"... Abstract. In this note we study positive solutions of the mth order ra-tional difference equation xn = (a0+ ..."
Abstract - Add to MetaCart
Abstract. In this note we study positive solutions of the mth order ra-tional difference equation xn = (a0+
Next 10 →
Results 1 - 10 of 1,728
Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University