用改进的ART-2网络建立移动机器人环境模型的研究

本文应用自适应共振理论中ART-2神经网络进行移动机器人环境障碍模式识别。ART-2神经网络在处理单方向渐变的模式输入时具有模式漂移的特点，机器人在静态环境中运动依赖这种特点，但在动态环境中模式漂移的特点却会对机器人的安全造成威胁。为此，设计了一种改进的ART-2神经网络，使得移动机器人同时适应在静态和动态环境中安全运动。

Tactile Sensing for Mechatronics: A State of the Art Survey

Lee M.H. and Nicholls H.R., Tactile Sensing for Mechatronics: A State of the Art Survey, Mechatronics, 9, Jan 1999, pp1-31.

ART: An ontology based tool for the translation of papers into Semantic Web format

To be presented at SIG/ISMB07 ontology workshop: http://bio-ontologies.org.uk/index.php To be published in BMC Bioinformatics. Sponsorship: JISC

Hugh Blaker: Doing his Bit for the Moderns

Meyrick, Robert, 'Hugh Blaker: Doing his Bit for the Moderns', Journal of the History of Collections (2004) 16(2):173-189 RAE2008

Wealth Wise and Culture Kind

Meyrick, Robert, 'Wealth Wise and Culture Kind', In: 'Things of Beauty: What Two Sisters did for Wales', (Cardiff: National Museum Wales Books), pp.96-111, 2007 RAE2008

From Art to Avant Garde? Television, Formalism and the Arts Documentary in 1960's Britain

Sexton, J. (2008). From Art to Avant Garde? Television, Formalism and the Arts Documentary in 1960's Britain. In L. Mulvey and J. Sexton (Eds.), Experimental British Television (pp.89-105). Manchester: Manchester University Press. RAE2008

„Moja osobista przestrzeń” – prywatne wirtualne kolekcje sztuki

The phenomenon analyzed in the essay My Personal Space – The Private Virtual Collections of Art is the possibility of visiting the world’s museums by means of the Internet – visiting indirect, nevertheless enabling peaceful, profound, multiple and free contemplation of art. The function of Mon espace personnel (My Personal Space) of French museums of Louvre and Orsay that reveals some radical modifications in the perception, understanding and reception of art, is an illustration of this phenomenon. Using Mon espace personnel means traversing the virtual Louvre or Orsay and choosing works of art, their descriptions, analyses, publications etc. and then adding them to the internaut’s personal thematic albums. The phenomenon described is a starting point to the reflection on the significance of the space in which art exists (called, according to Golka, the form of art’s presence) with its ontology as well as its functions and the character of its reception. The identification of what this space is, in the context of the hybridization of the form and the content and the emergence of the computer culture (Manovich) as well as in the context of the popularization of the reality (Krajewski) and the decentralization of the world of art (Wójtowicz), is an important part of this essay. These phenomena are also inscribed in a wider context of the changes of the character, mission and role of the museum in the time of the digital revolution.

Bring ART into the ACT

ACT is compared with a particular type of connectionist model that cannot handle symbols and use non-biological operations that cannot learn in real time. This focus continues an unfortunate trend of straw man "debates" in cognitive science. Adaptive Resonance Theory, or ART, neural models of cognition can handle both symbols and sub-symbolic representations, and meets the Newell criteria at least as well as these models.

Biased ART: A Neural Architecture that Shifts Attention Toward Previously Disregarded Features Following an Incorrect Prediction

Memories in Adaptive Resonance Theory (ART) networks are based on matched patterns that focus attention on those portions of bottom-up inputs that match active top-down expectations. While this learning strategy has proved successful for both brain models and applications, computational examples show that attention to early critical features may later distort memory representations during online fast learning. For supervised learning, biased ARTMAP (bARTMAP) solves the problem of over-emphasis on early critical features by directing attention away from previously attended features after the system makes a predictive error. Small-scale, hand-computed analog and binary examples illustrate key model dynamics. Twodimensional simulation examples demonstrate the evolution of bARTMAP memories as they are learned online. Benchmark simulations show that featural biasing also improves performance on large-scale examples. One example, which predicts movie genres and is based, in part, on the Netflix Prize database, was developed for this project. Both first principles and consistent performance improvements on all simulation studies suggest that featural biasing should be incorporated by default in all ARTMAP systems. Benchmark datasets and bARTMAP code are available from the CNS Technology Lab Website: http://techlab.bu.edu/bART/.

On the Relationship Between the Generalized Equality Classifier and ART 2 Neural Networks

In this paper, we introduce the Generalized Equality Classifier (GEC) for use as an unsupervised clustering algorithm in categorizing analog data. GEC is based on a formal definition of inexact equality originally developed for voting in fault tolerant software applications. GEC is defined using a metric space framework. The only parameter in GEC is a scalar threshold which defines the approximate equality of two patterns. Here, we compare the characteristics of GEC to the ART2-A algorithm (Carpenter, Grossberg, and Rosen, 1991). In particular, we show that GEC with the Hamming distance performs the same optimization as ART2. Moreover, GEC has lower computational requirements than AR12 on serial machines.