AI 2006: Advances in Artificial Intelligence: 19th by Hiroshi Motoda (auth.), Abdul Sattar, Byeong-ho Kang (eds.)

By Hiroshi Motoda (auth.), Abdul Sattar, Byeong-ho Kang (eds.)

The Australian Joint convention on synthetic Intelligence sequence is instructed via the Australian computing device Society's (ACS) nationwide Committee on synthetic Intelligence and professional structures. It goals at stimulating study by way of selling trade and cross-fertilization of principles between assorted branches of man-made intelligence. It additionally presents a standard discussion board for researchers and practitioners in numerous fields of AI to replace new principles and percentage their event. This quantity includes the lawsuits of the nineteenth Australian Joint convention on synthetic Intelligence (AI 2006) held at Hobart, Australia. AI 2006 bought a checklist variety of submissions, a complete of 689 submissions from 35 nations. From those, complete papers 89 (13%), lengthy papers (up to twelve pages) and 70 (10%) brief papers (up to 7 pages) have been accredited for presentation and integrated during this quantity. All complete papers have been reviewed via rounds of tests by means of at the very least autonomous - audience together with Senior software Committee participants. The papers during this quantity supply a sign of contemporary advances in man made int- ligence. the subjects lined contain computing device studying, Robotics, AI functions, making plans, brokers, information Mining and information Discovery, Cognition and person Interface, imaginative and prescient and snapshot Processing, details Retrieval and seek, AI within the internet, wisdom illustration, Knowledge-Based platforms, and Neural Networks.

Show description

Read or Download AI 2006: Advances in Artificial Intelligence: 19th Australian Joint Conference on Artificial Intelligence, Hobart, Australia, December 4-8, 2006. Proceedings PDF

Best computers books

Oracle Enterprise Manager. Messages Manual

This guide offers possible explanations and prompt activities for mistakes messages generated by means of Oracle firm supervisor and its elements, together with the not obligatory administration packs.

Lectures on Concurrency and Petri Nets: Advances in Petri Nets

This instructional quantity originates from the 4th complicated direction on Petri Nets, ACPN 2003, held in Eichst? tt, Germany in September 2003. as well as lectures given at ACPN 2003, extra chapters were commissioned to offer a well-balanced presentation of the state-of-the-art within the sector. This ebook may be helpful as either a reference for these operating within the region in addition to a research publication for the reader who's attracted to an updated review of analysis and improvement in concurrent and dispensed platforms; in fact, readers in particular attracted to theoretical or applicational facets of Petri nets will get pleasure from the ebook to boot.

Languages and Compilers for High Performance Computing: 17th International Workshop, LCPC 2004, West Lafayette, IN, USA, September 22-24, 2004, Revised ... Computer Science and General Issues)

This publication constitutes the completely refereed post-proceedings of the seventeenth overseas Workshop on Languages and Compilers for top functionality Computing, LCPC 2004, held in West Lafayette, IN, united states in September 2004. The 33 revised complete papers offered have been rigorously chosen in the course of rounds of reviewing and development.

Additional resources for AI 2006: Advances in Artificial Intelligence: 19th Australian Joint Conference on Artificial Intelligence, Hobart, Australia, December 4-8, 2006. Proceedings

Sample text

ACLP [8] extends abductive logic programming with constraints. It uses a version of SCA (where C is f alse) in its algorithm but it does not perform abduction on constraints, only on formulas that may involve constraints. It is easy to see that there is always an answer to a SCA problem by taking A to be C. However, in general there may be infinitely many answers, and we will need a finite representation. For example, if B is x ≥ 5 and C is x ≥ 7 then C is an answer, but so is every constraint x ≥ k where k ≥ 7.

In this paper, which is a direct continuation of work presented in [23,24], we model the processing of phonemes and letters both in sensory-specific areas and in sensory integration. The network we use for this study is a multimodal selforganizing network (MuSON) which consists of unimodal maps with phonetic and graphic inputs respectively, and an integrating bimodal map. These maps correspond to the cortical architecture for phonetic processing in the STSp, processing of letters in the fusiform area and the bimodal integration in the STS.

Feedback in MuSON Enhances Perception of Corrupted Stimuli 21 We have earlier shown [24] in a study without feedback how templates for phonemes and letters result from self-organization of the unimodal maps and integrate into templates for the bimodal percepts in the bimodal map. We have also shown that the bimodal percepts are robust against additive noise in the letters and phonemes. The purpose of this study is to show how this robustness of the bimodal percepts can be “transferred” down in the processing stream by feedback.

Download PDF sample

Rated 5.00 of 5 – based on 16 votes