Artificial Neural Networks - ICANN 2010

1. Front Matter

   PDF

2. Kernel Algorithms – Support Vector Machines

   1. Convergence Improvement of Active Set Training for Support Vector Regressors

      • Shigeo Abe, Ryousuke Yabuwaki

      Pages 1-10

   2. The Complex Gaussian Kernel LMS Algorithm

      • Pantelis Bouboulis, Sergios Theodoridis

      Pages 11-20

   3. Support Vector Machines-Kernel Algorithms for the Estimation of the Water Supply in Cyprus

      • Fotis Maris, Lazaros Iliadis, Stavros Tachos, Athanasios Loukas, Iliana Spartali, Apostolos Vassileiou et al.

      Pages 21-29

   4. Faster Directions for Second Order SMO

      • Álvaro Barbero, José R. Dorronsoro

      Pages 30-39

   5. Almost Random Projection Machine with Margin Maximization and Kernel Features

      • Tomasz Maszczyk, Włodzisław Duch

      Pages 40-48

   6. A New Tree Kernel Based on SOM-SD

      • Fabio Aiolli, Giovanni Da San Martino, Alessandro Sperduti

      Pages 49-58

   7. Kernel-Based Learning from Infinite Dimensional 2-Way Tensors

      • Marco Signoretto, Lieven De Lathauwer, Johan A. K. Suykens

      Pages 59-69

   8. Semi-supervised Facial Expressions Annotation Using Co-Training with Fast Probabilistic Tri-Class SVMs

      • Mohamed Farouk Abdel Hady, Martin Schels, Friedhelm Schwenker, Günther Palm

      Pages 70-75

   9. An Online Incremental Learning Support Vector Machine for Large-scale Data

      • Jun Zheng, Hui Yu, Furao Shen, Jinxi Zhao

      Pages 76-81

   10. A Common Framework for the Convergence of the GSK, MDM and SMO Algorithms

       • Jorge López, José R. Dorronsoro

       Pages 82-87

   11. The Support Feature Machine for Classifying with the Least Number of Features

       • Sascha Klement, Thomas Martinetz

       Pages 88-93

3. Knowledge Engineering and Decision Making

   1. Hidden Markov Model for Human Decision Process in a Partially Observable Environment

      • Masahiro Adomi, Yumi Shikauchi, Shin Ishii

      Pages 94-103

   2. Representing, Learning and Extracting Temporal Knowledge from Neural Networks: A Case Study

      • Rafael V. Borges, Artur d’Avila Garcez, Luis C. Lamb

      Pages 104-113

4. Recurrent ANN

   1. Multi-Dimensional Deep Memory Atari-Go Players for Parameter Exploring Policy Gradients

      • Mandy Grüttner, Frank Sehnke, Tom Schaul, Jürgen Schmidhuber

      Pages 114-123

   2. Layered Motion Segmentation with a Competitive Recurrent Network

      • Julian Eggert, Joerg Deigmoeller, Volker Willert

      Pages 124-133

   3. Selection of Training Data for Locally Recurrent Neural Network

      • Krzysztof Patan, Maciej Patan

      Pages 134-137

   4. A Statistical Appraoch to Image Reconstruction from Projections Problem Using Recurrent Neural Network

      • Robert Cierniak

      Pages 138-141

   5. A Computational System of Metaphor Generation with Evaluation Mechanism

      • Asuka Terai, Masanori Nakagawa

      Pages 142-147

   6. Recurrence Enhances the Spatial Encoding of Static Inputs in Reservoir Networks

      • Christian Emmerich, René Felix Reinhart, Jochen Jakob Steil

      Pages 148-153

th This volume is part of the three-volume proceedings of the 20 International Conference on Arti?cial Neural Networks (ICANN 2010) that was held in Th- saloniki, Greece during September 15–18, 2010. ICANN is an annual meeting sponsored by the European Neural Network Society (ENNS) in cooperation with the International Neural Network So- ety (INNS) and the Japanese Neural Network Society (JNNS). This series of conferences has been held annually since 1991 in Europe, covering the ?eld of neurocomputing, learning systems and other related areas. As in the past 19 events, ICANN 2010 provided a distinguished, lively and interdisciplinary discussion forum for researches and scientists from around the globe. Ito?eredagoodchanceto discussthe latestadvancesofresearchandalso all the developments and applications in the area of Arti?cial Neural Networks (ANNs). ANNs provide an information processing structure inspired by biolo- cal nervous systems and they consist of a large number of highly interconnected processing elements (neurons). Each neuron is a simple processor with a limited computing capacity typically restricted to a rule for combining input signals (utilizing an activation function) in order to calculate the output one. Output signalsmaybesenttootherunitsalongconnectionsknownasweightsthatexcite or inhibit the signal being communicated. ANNs have the ability “to learn” by example (a large volume of cases) through several iterations without requiring a priori ?xed knowledge of the relationships between process parameters.

• Hidden Markov Model
• Markov Model
• Support Vector Machine
• algorithms
• artificial intelligence
• brain-computer interfaces
• classification
• computational neuroscience
• evolutionary algorithms
• genetic algorithms
• knowledge engineering
• machine learning
• recurrent neural netw
• robot vision
• visualization
• algorithm analysis and problem complexity

• Department of Informatics, TEI of Thessaloniki, Sindos, Greece

  Konstantinos Diamantaras

• School of Physics, Astronomy, and Informatics, Department of Informatics, Nicolaus Copernicus University, Torun, Poland

  Wlodek Duch

• Department of Forestry and Management of the Environment and Natural Resources, Democritus University of Thrace, Orestiada Thrace, Greece

  Lazaros S. Iliadis

Policies and ethics