TY - CONF AU - Lőrincz, András AU - Faragó, Kinga Bettina AU - Fóthi, Áron AU - Milacski, Zoltán Ádám AU - Bryar, Rahman AU - Sárkány, András AU - Varga, Viktor ED - Sandamirskaya, Yulia TI - Episode clustering and episodic labeling. The meeting point of artificial intelligence, deep neural networks, and human intelligence TS - The meeting point of artificial intelligence, deep neural networks, and human intelligence T2 - Learning PY - 2017 SP - 20 EP - 22 PG - 3 UR - https://m2.mtmt.hu/api/publication/31880767 ID - 31880767 N1 - 3in(EFOP-3.6.2-16-2017-00013) Támogató: EFOP Innovatív Informatikai és Infokommunikációs Megoldásokat Megalapozó Tematikus Kutatási Együttműködések LA - English DB - MTMT ER - TY - BOOK ED - Horváth, Zoltán ED - Kozma, László ED - Zsók, Viktória TI - Proceedings of the 10th Symposium on Programming Languages and Software Tools. SPLST 2007 : Dobogókő, Hungary, 14-16 June 2007 TS - SPLST 2007 : Dobogókő, Hungary, 14-16 June 2007 ET - 0 PB - Eötvös Loránd University Press CY - Budapest PY - 2007 SP - 491 SN - 9789634639251 UR - https://m2.mtmt.hu/api/publication/1653130 ID - 1653130 LA - English DB - MTMT ER - TY - CONF AU - Istenes, Zoltán AU - Kozsik, Tamás AU - Hoch, Csaba AU - Tóth, László Attila ED - Csörnyei, Zoltán TI - Proving the Correctness of Mobile Code in B T2 - 6th Joint Conference on Mathematics and Computer Science, MaCS ’06 C1 - Pécs PY - 2006 SP - 45 UR - https://m2.mtmt.hu/api/publication/1962642 ID - 1962642 N1 - Full paper: PU.M.A. 17(3-4):323-342, 2006 LA - English DB - MTMT ER - TY - JOUR AU - Istenes, Zoltán AU - Kozsik, Tamás AU - Hoch, Csaba AU - Tóth, László Attila TI - Proving the correctness of mobile Java code JF - PURE MATHEMATICS AND APPLICATIONS J2 - PU.M.A PURE MATH APPL VL - 17 PY - 2006 IS - 3-4 SP - 323 EP - 342 PG - 20 SN - 1218-4586 UR - https://m2.mtmt.hu/api/publication/1639730 ID - 1639730 LA - English DB - MTMT ER - TY - JOUR AU - Lőrincz, András AU - Kókai, I AU - Meretei, A TI - Intelligent high-performance crawlers used to reveal topic-specific structure of the www JF - INTERNATIONAL JOURNAL OF FOUNDATIONS OF COMPUTER SCIENCE J2 - INT J FOUND COMPUT S VL - 13 PY - 2002 IS - 4 SP - 477 EP - 495 PG - 19 SN - 0129-0541 DO - 10.1142/S0129054102001230 UR - https://m2.mtmt.hu/api/publication/2597911 ID - 2597911 AB - The slogan that «information is power» has undergone a slight change. Today, «information updating» is in the focus of interest. The largest source of information today is the World Wide Web. Fast search methods are needed to utilize this enormous source of information. In this paper our novel crawler using support vector classification and on-line reinforcement learning is described. We launched crawler searches from different sites, including sites that offer, at best, very limited information about the search subject. This case may correspond to typical searches of non-experts. Results indicate that the considerable performance improvement of our crawler over other known crawlers is due to its on-line adaptation property. We used our crawler to characterize basic topic-specific properties of WWW environments. It was found that topic-specific regions have a broad distribution of valuable documents. Expert sites are excellent starting points, whereas mailing lists can form trape for the crawler. These properties of the WWW and the emergence of intelligent «high-performance» crawlers that monitor and search for novel information together predict a significant increase of communication load on the WWW in the near future. © 2002 World Scientific Publishing Company. LA - English DB - MTMT ER - TY - JOUR AU - Lőrincz, András AU - Szirtes, G AU - Takács, B AU - Biederman, I AU - Vogels, R TI - Relating priming and repetition suppression. JF - INTERNATIONAL JOURNAL OF NEURAL SYSTEMS J2 - INT J NEURAL SYST VL - 12 PY - 2002 IS - 3-4 SP - 187 EP - 201 PG - 15 SN - 0129-0657 UR - https://m2.mtmt.hu/api/publication/2097495 ID - 2097495 AB - We present a prototype of a recently proposed two stage model of the entorhinal-hippocampal loop. Our aim is to form a general computational model of the sensory neocortex. The model--grounded on pure information theoretic principles--accounts for the most characteristic features of long-term memory (LTM), performs bottom-up novelty detection, and supports noise filtering. Noise filtering can also serve to correct the temporal ordering of information processing. Surprisingly, as we examine the temporal characteristics of the model, the emergent dynamics can be interpreted as perceptual priming, a fundamental type of implicit memory. In the model's framework, computational results support the hypothesis of a strong correlation between perceptual priming and repetition suppression and this correlation is a direct consequence of the temporal ordering in forming the LTM. We also argue that our prototype offers a relatively simple and coherent explanation of priming and its relation to a general model of information processing by the brain. LA - English DB - MTMT ER - TY - JOUR AU - Lőrincz, András AU - Póczos, B AU - Szirtes, G AU - Takács, B TI - Ockham's razor at work: Modeling of the "homunculus" JF - BRAIN AND MIND J2 - BRAIN MIND VL - 3 PY - 2002 IS - 2 SP - 187 EP - 220 PG - 34 SN - 1389-1987 DO - 10.1023/A:1019996320835 UR - https://m2.mtmt.hu/api/publication/2097494 ID - 2097494 AB - There is a broad consensus about the fundamental role of the hippocampal system (hippocampus and its adjacent areas) in the encoding and retrieval of episodic memories. This paper presents a functional model of this system. Although memory is not a single-unit cognitive function, we took the view that the whole system of the smooth, interrelated memory processes may have a common basis. That is why we follow the Ockham's razor principle and minimize the size or complexity of our model assumption set. The fundamental assumption is the requirement of solving the so called "homunculus fallacy", which addresses the issue of interpreting the input. Generative autoassociators seem to offer a resolution of the paradox. Learning to represent and to recall information, in these generative networks, imply maximization of information transfer, sparse representation and novelty recognition. A connectionist architecture, which integrates these aspects as model constraints, is derived. Numerical studies demonstrate the novelty recognition and noise filtering properties of the architecture. Finally, we conclude that the derived connectionist architecture can be related to the neurobiological substrate. LA - English DB - MTMT ER - TY - JOUR AU - Kókai, I AU - Lőrincz, András TI - Fast adapting value estimation-based hybrid architecture for searching the world-wide web JF - APPLIED SOFT COMPUTING J2 - APPL SOFT COMPUT VL - 2 PY - 2002 IS - 1 SP - 11 EP - 23 PG - 13 SN - 1568-4946 DO - 10.1016/S1568-4946(02)00025-X UR - https://m2.mtmt.hu/api/publication/2097493 ID - 2097493 AB - The slogan that information is power has undergone a slight change. Today, information updating is in the focus of interest. The largest source of information is the world-wide web. Fast search methods are in need for this enormous source. In this paper a hybrid architecture that combines soft support vector classification and reinforcement learning for value estimation is introduced for the evaluation of a link (a document) and its neighboring links (or documents), called the context of a document. The method is motivated by (i) large differences between such contexts on the web, (ii) the facilitation of goal oriented search using context classifiers, and (iii) attractive fast adaptation properties, that could counteract diversity of web environments. We demonstrate that value estimation-based fast adaptation offers considerable improvement over other known search methods. © 2002 Elsevier Science B.V. All rights reserved. LA - English DB - MTMT ER - TY - CHAP AU - Farkas, C AU - Meretei, A AU - Ziegler, Gábor AU - Lőrincz, András ED - De Capitani, di Vimercati S ED - Samarati, P TI - Anonymity and accountability in self-organizing electronic communities T2 - ACM Workshop on Privacy in the Electronic Society PB - ACM Press CY - New York, New York SN - 9781581136333 T3 - Proceedings of the ACM Conference on Computer and Communications Security PY - 2002 SP - 81 EP - 90 PG - 10 DO - 10.1145/644527.644536 UR - https://m2.mtmt.hu/api/publication/2097491 ID - 2097491 AB - In this paper we study the problem of anonymity versus accountability in electronic communities. We argue that full anonymity may present a security risk that is unacceptable in certain applications; therefore, anonymity and accountability are both needed. To resolve the inherent contradiction between anonymity and accountability in a flexible manner, we introduce the concepts of internal and external accountabilities. Intuitively, internal accountability applies to virtual users only, and is governed by the policy of a group (a community). In contrast, external accountability is needed to address issues related to misuse if the activity is to be penalized in real life according to internal rules or external laws. We provide a set of protocols to ensure that users' virtual and real identities cannot be disclosed unnecessarily, and allow users to monitor the data collected about them as well as to terminate their membership (both real and virtual) under certain conditions. We develop a general conceptual model of electronic Editorial Board (e-EB). In our thinking, there are deep connections between anonymity and self-organization. In turn, the concept of self-organizing e-EB (SO-eEB) is introduced here, and a robotic example is provided. Finally, SO-eEB is specialized to Anonymous and Accountable Self-Organizing Communities (A2SOCs), that fully supports internal and external accountability while providing anonymity. LA - English DB - MTMT ER - TY - JOUR AU - Lőrincz, András AU - Szatmary, B AU - Szirtes, G TI - The mystery of structure and function of sensory processing areas of the neocortex: A resolution JF - JOURNAL OF COMPUTATIONAL NEUROSCIENCE J2 - J COMPUT NEUROSCI VL - 13 PY - 2002 IS - 3 SP - 187 EP - 205 PG - 19 SN - 0929-5313 DO - 10.1023/A:1020262214821 UR - https://m2.mtmt.hu/api/publication/2072373 ID - 2072373 LA - English DB - MTMT ER -