Artificial Neural Networks and Machine Learning -- ICANN 2014

1. Front Matter

   PDF

2. Recurrent Networks

   1. Sequence Learning

      1. Dynamic Cortex Memory: Enhancing Recurrent Neural Networks for Gradient-Based Sequence Learning

         • Sebastian Otte, Marcus Liwicki, Andreas Zell

         Pages 1-8

      2. Learning and Recognition of Multiple Fluctuating Temporal Patterns Using S-CTRNN

         • Shingo Murata, Hiroaki Arie, Tetsuya Ogata, Jun Tani, Shigeki Sugano

         Pages 9-16

      3. Regularized Recurrent Neural Networks for Data Efficient Dual-Task Learning

         • Sigurd Spieckermann, Siegmund Düll, Steffen Udluft, Thomas Runkler

         Pages 17-24

   2. Echo State Networks

      1. On-line Training of ESN and IP Tuning Effect

         • Petia Koprinkova-Hristova

         Pages 25-32

      2. An Incremental Approach to Language Acquisition: Thematic Role Assignment with Echo State Networks

         • Xavier Hinaut, Stefan Wermter

         Pages 33-40

      3. Memory Capacity of Input-Driven Echo State Networks at the Edge of Chaos

         • Peter Barančok, Igor Farkaš

         Pages 41-48

      4. Adaptive Critical Reservoirs with Power Law Forgetting of Unexpected Input Sequences

         • Norbert Michael Mayer

         Pages 49-56

   3. Recurrent Network Theory

      1. Interactive Evolving Recurrent Neural Networks Are Super-Turing Universal

         • Jérémie Cabessa, Alessandro E. P. Villa

         Pages 57-64

      2. Attractor Metadynamics in Adapting Neural Networks

         • Claudius Gros, Mathias Linkerhand, Valentin Walther

         Pages 65-72

      3. Basic Feature Quantities of Digital Spike Maps

         • Hiroki Yamaoka, Narutoshi Horimoto, Toshimichi Saito

         Pages 73-80

3. Competitive Learning and Self-Organisation

   1. Discriminative Fast Soft Competitive Learning

      • Frank-Michael Schleif

      Pages 81-88

   2. Human Action Recognition with Hierarchical Growing Neural Gas Learning

      • German Ignacio Parisi, Cornelius Weber, Stefan Wermter

      Pages 89-96

   3. Real-Time Anomaly Detection with a Growing Neural Gas

      • Nicolai Waniek, Simon Bremer, Jörg Conradt

      Pages 97-104

   4. Classification with Reject Option Using the Self-Organizing Map

      • Ricardo Sousa, Ajalmar R. da Rocha Neto, Jaime S. Cardoso, Guilherme A. Barreto

      Pages 105-112

4. Clustering and Classification

   1. A Non-parametric Maximum Entropy Clustering

      • Hideitsu Hino, Noboru Murata

      Pages 113-120

   2. Instance Selection Using Two Phase Collaborative Neighbor Representation

      • Fadi Dornaika, I. Kamal Aldine

      Pages 121-128

   3. Global Metric Learning by Gradient Descent

      • Jens Hocke, Thomas Martinetz

      Pages 129-135

   4. Leaving Local Optima in Unsupervised Kernel Regression

      • Daniel Lückehe, Oliver Kramer

      Pages 137-144

5. Trees and Graphs

   1. An Algorithm for Directed Graph Estimation

      • Hideitsu Hino, Atsushi Noda, Masami Tatsuno, Shotaro Akaho, Noboru Murata

      Pages 145-152

The book constitutes the proceedings of the 24th International Conference on Artificial Neural Networks, ICANN 2014, held in Hamburg, Germany, in September 2014.
The 107 papers included in the proceedings were carefully reviewed and selected from 173 submissions. The focus of the papers is on following topics: recurrent networks; competitive learning and self-organisation; clustering and classification; trees and graphs; human-machine interaction; deep networks; theory; reinforcement learning and action; vision; supervised learning; dynamical models and time series; neuroscience; and applications.

• computational neuroscience
• distributed computation
• dynamical systems
• ensemble methods
• evolving systems
• machine learning
• neural networks
• parallel distributed system
• particle swarm optimization
• reinforcement learning
• robust pattern recognition
• self-organizing maps
• speech recognition
• support vector machines
• swarm intelligence
• turing machines
• unsupervised learning
• algorithm analysis and problem complexity

• Department of Informatics, University of Hamburg, Hamburg, Germany

  Stefan Wermter, Cornelius Weber, Sven Magg

• Department of Informatics, Nicolaus Compernicus University, Torun, Poland

  Włodzisław Duch

• Department of Modern Languages, University of Helsinki, Helsinki, Finland

  Timo Honkela

• Institute of Information and Communication Technologies, Bulgarian Academy of Sciences, Sofia, Bulgaria

  Petia Koprinkova-Hristova

• Institute of Neural Information Processing, University of Ulm, Oberer Eselsberg, Germany

  Günther Palm

• Department of Information Systems, Quartier UNIL-Dorigny, Bâtiment Internef, University of Lausanne, Lausanne, Switzerland

  Alessandro E. P. Villa

Policies and ethics