By Michael G. Madden (auth.), Max Bramer BSc, PhD, CEng, CITP, FBCS, FIET, FRSA, FHEA, Miltos Petridis DipEng, MBA, PhD, MBCS, AMBA, Frans Coenen BSc, PhD (eds.)

The papers during this quantity are the refereed technical papers offered at AI-2008, the Twenty-eighth SGAI foreign convention on cutting edge ideas and purposes of synthetic Intelligence, held in Cambridge in December 2008.

They current new and cutting edge advancements within the box, divided into sections on CBR and category, AI strategies, Argumentation and Negotiation, clever structures, From desktop studying To E-Learning and determination Making. the amount additionally comprises the textual content of brief papers offered as posters on the conference.

This is the twenty-fifth quantity within the study and improvement sequence. The sequence is vital analyzing if you happen to desire to sustain so far with advancements during this very important field.

The software move papers are released as a better half quantity below the identify functions and techniques in clever platforms XVI.

Show description

Read or Download Research and Development in Intelligent Systems XXV: Proceedings of AI-2008, the Twenty-eighth SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence PDF

Best research books

Singapore's World-Class Research (Seri: Singapore Eye Research Institute)

Simply 10 years in the past, ophthalmic learn was once virtually exceptional in Singapore. With little funds and no infrastructure, ophthalmologists and scientists expressed scant curiosity in examine. this day, in spite of the fact that, ophthalmic learn in Singapore is at a excessive foreign point, as exemplified via the actions of the Singapore Eye learn Institute (SERI), that's able to competing with and tough the world's major eye learn facilities.

Membrane Research: Classic Origins and Current Concepts

Membrane examine: vintage Origins and present options is a unique quantity of the foreign evaluate of Cytology devoted to Dr. Danielli at the social gathering of his retirement from legit tasks. The principal subject matter of the quantity is membranes. the range of issues levels from the biogenesis of membranes and their elements, to using optical and lectin probes as a way to check the constitution, body structure, and interactions of telephone elements and organelles in plant and animal structures.

Machine Translation: From Research to Real Users: 5th Conference of the Association for Machine Translation in the Americas, AMTA 2002 Tiburon, CA, USA, October 8 – 12, 2002 Proceedings

AMTA 2002: From examine to actual clients Ever because the showdown among Empiricists and Rationalists a decade in the past at TMI ninety two, MT researchers have hotly pursued promising paradigms for MT, together with da- pushed techniques (e. g. , statistical, example-based) and hybrids that combine those with extra conventional rule-based elements.

Extra info for Research and Development in Intelligent Systems XXV: Proceedings of AI-2008, the Twenty-eighth SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence

Example text

In this approach, a template or a prototype of the pattern is generated and compared 36 Jayaraman J. Thiagarajan, Karthikeyan N. Ramamurthy and Andreas Spanias to the test pattern to be recognized, taking into account the random transformations that might have occurred in the test pattern. The metric for similarity is often a correlation measure, but if the template is modeled statistically, a likelihood measure can be used. A statistical model using wavelet transforms has been used to obtain a sparse representation template and the generated template has been used for pattern classification [6].

We estimate statistical templates in the data representation domain for each class of data, and perform classification using a likelihood measure. Simulation results show that, in the case of highly sparse signals, the proposed classifier provides a consistently good performance even under noisy conditions. 1 Introduction Sparse approximations of signals over an overcomplete dictionary aim to find a low cost solution in terms of coefficient sparsity with a constraint on the reconstruction error. Redundant representations have proven to be more robust in presence of noise, and provide flexibility in representing the signals using an overcomplete set of basis functions [4].

MIT Press (2006). 4. Olshausen, A. : Sparse Coding with an Overcomplete Basis Set: A Strategy Employed by V1? Vision Research. 37(23), 3311–3325 (1996). 5. : What is the Goal of Sensory Coding?. Neural Computation. 6, 559–601 (1994). 6. Scott, C. : TEMPLAR: a wavelet-based framework for pattern learning and analysis. IEEE Transactions on Signal Processing. 52(8), 2264–2274 (2000). 7. Mallat, S. : Matching Pursuits with Time-Frequency Dictionaries. IEEE Transactions on Signal Processing. 41(12), 3397–3415 (1999).

Download PDF sample

Rated 4.87 of 5 – based on 50 votes