Mani Abedini, Michael Kirley (auth.), Dianhui Wang, Mark's AI 2011: Advances in Artificial Intelligence: 24th PDF

By Mani Abedini, Michael Kirley (auth.), Dianhui Wang, Mark Reynolds (eds.)

ISBN-10: 364225831X

ISBN-13: 9783642258312

This booklet constitutes the refereed lawsuits of the twenty fourth Australasian Joint convention on synthetic Intelligence, AI 2011, held in Perth, Australia, in December 2011. The eighty two revised complete papers awarded have been conscientiously reviewed and chosen from 193 submissions. The papers are prepared in topical sections on information mining and data discovery, laptop studying, evolutionary computation and optimization, clever agent structures, good judgment and reasoning, imaginative and prescient and portraits, photograph processing, typical language processing, cognitive modeling and simulation know-how, and AI applications.

Show description

Read Online or Download AI 2011: Advances in Artificial Intelligence: 24th Australasian Joint Conference, Perth, Australia, December 5-8, 2011. Proceedings PDF

Similar nonfiction_5 books

Rockwood and Matsen's The Shoulder: Expert Consult - Online - download pdf or read online

Considerably revised and up-to-date, the hot version of this very hot reference at the shoulder maintains to provoke. a large number of top foreign authorities-30% new to this 4th edition-present present day so much complete, in-depth view of the present kingdom of shoulder perform, all in a superbly illustrated, full-color 2-volume masterwork.

Download e-book for kindle: Early Experience and the Life Path by Ann M. Clarke, Alan D. B. Clarke

This article concludes at the foundation of empirical facts that theories which ascribe overriding value to the early years are faulty. The authors study the wide-ranging theoretical and functional implications in their findings. there's no indication that early reviews are unimportant; yet they signify not more than the 1st steps in an ongoing and intricate lifestyles direction, on which the shaping or re-shaping of improvement can ensue in any interval.

Additional resources for AI 2011: Advances in Artificial Intelligence: 24th Australasian Joint Conference, Perth, Australia, December 5-8, 2011. Proceedings

Example text

References 1. : Imposing tree-based topologies onto self organizing maps. Information Sciences 181(18), 3798–3815 (2011) 2. : Modern Information Retrieval. , Boston (1999) 3. : Clustering unlabeled data with SOMs improves classification of labeled real-world data. In: Proc. of the 2002 International Joint Conference on Neural Networks, IJCNN 2002, vol. 3, pp. 2237–2242 (2002) 4. : Semi-supervised clustering using genetic algorithms. In: Artificial Neural Networks in Engineering (ANNIE 1999), pp.

The three classifiers utilized the same parameters, which are described in Section 4. Besides, while the LVQ1 and the SOM utilized 128 neurons, the results shown for the TTOSOM include only 15 neurons. As per our results, the TTOSOM, using only a small percentage of the neurons used in the SOM and LVQ1 (almost 10%), outperforms their recognition capabilities in all six datasets. Apart from the above, observe that the classification results offered by the TTOSOM are comparable to the ones obtained by the k-NN.

This paper presents a classifier which uses a tree-based Neural Network (NN), and uses both, unlabeled and labeled instances. First, we learn the structure of the data distribution in an unsupervised manner. After convergence, and once labeled data become available, our strategy tags each of the clusters according to the evidence provided by the instances. Unlike other neighborhood-based schemes, our classifier uses only a small set of representatives whose cardinality can be much smaller than that of the input set.

Download PDF sample

AI 2011: Advances in Artificial Intelligence: 24th Australasian Joint Conference, Perth, Australia, December 5-8, 2011. Proceedings by Mani Abedini, Michael Kirley (auth.), Dianhui Wang, Mark Reynolds (eds.)


by John
4.0

Rated 4.29 of 5 – based on 17 votes