Artificial Neural Networks in Pattern Recognition

1. Front Matter

   Pages I-XI

   PDF

2. Invited Papers

   1. Front Matter

      Pages 1-1

      PDF

   2. What’s Wrong with Computer Vision?

      • Marco Gori

      Pages 3-16

   3. Deep Learning in the Wild

      • Thilo Stadelmann, Mohammadreza Amirian, Ismail Arabaci, Marek Arnold, Gilbert François Duivesteijn, Ismail Elezi et al.

      Pages 17-38

3. Learning Algorithms and Architectures

   1. Front Matter

      Pages 39-39

      PDF

   2. Effect of Equality Constraints to Unconstrained Large Margin Distribution Machines

      • Shigeo Abe

      Pages 41-53

   3. DLL: A Fast Deep Neural Network Library

      • Baptiste Wicht, Andreas Fischer, Jean Hennebert

      Pages 54-65

   4. Selecting Features from Foreign Classes

      • Ludwig Lausser, Robin Szekely, Viktor Kessler, Friedhelm Schwenker, Hans A. Kestler

      Pages 66-77

   5. A Refinement Algorithm for Deep Learning via Error-Driven Propagation of Target Outputs

      • Vincenzo Laveglia, Edmondo Trentin

      Pages 78-89

   6. Combining Deep Learning and Symbolic Processing for Extracting Knowledge from Raw Text

      • Andrea Zugarini, Jérémy Morvan, Stefano Melacci, Stefan Knerr, Marco Gori

      Pages 90-101

   7. SeNA-CNN: Overcoming Catastrophic Forgetting in Convolutional Neural Networks by Selective Network Augmentation

      • Abel Zacarias, Luís A. Alexandre

      Pages 102-112

   8. Classification Uncertainty of Deep Neural Networks Based on Gradient Information

      • Philipp Oberdiek, Matthias Rottmann, Hanno Gottschalk

      Pages 113-125

   9. Learning Neural Models for End-to-End Clustering

      • Benjamin Bruno Meier, Ismail Elezi, Mohammadreza Amirian, Oliver Dürr, Thilo Stadelmann

      Pages 126-138

   10. A \(k\)-Nearest Neighbor Based Algorithm for Multi-Instance Multi-Label Active Learning

       • Adrian T. Ruiz, Patrick Thiam, Friedhelm Schwenker, Günther Palm

       Pages 139-151

   11. Manifold Learning Regression with Non-stationary Kernels

       • Alexander Kuleshov, Alexander Bernstein, Evgeny Burnaev

       Pages 152-164

   12. F-Measure Curves for Visualizing Classifier Performance with Imbalanced Data

       • Roghayeh Soleymani, Eric Granger, Giorgio Fumera

       Pages 165-177

   13. Maximum-Likelihood Estimation of Neural Mixture Densities: Model, Algorithm, and Preliminary Experimental Evaluation

       • Edmondo Trentin

       Pages 178-189

   14. Generating Bounding Box Supervision for Semantic Segmentation with Deep Learning

       • Simone Bonechi, Paolo Andreini, Monica Bianchini, Franco Scarselli

       Pages 190-200

   15. Inductive–Transductive Learning with Graph Neural Networks

       • Alberto Rossi, Matteo Tiezzi, Giovanna Maria Dimitri, Monica Bianchini, Marco Maggini, Franco Scarselli

       Pages 201-212

   16. Bounded Rational Decision-Making with Adaptive Neural Network Priors

       • Heinke Hihn, Sebastian Gottwald, Daniel A. Braun

       Pages 213-225Open Access

This book constitutes the refereed proceedings of the 8th IAPR TC3 International Workshop on Artificial Neural Networks in Pattern Recognition, ANNPR 2018, held in Siena, Italy, in September 2018.


The 29 revised full papers presented together with 2 invited papers were carefully reviewed and selected from 35 submissions. The papers present and discuss the latest research in all areas of neural network- and machine learning-based pattern recognition. They are organized in two sections: learning algorithms and architectures, and applications. 


Chapter "Bounded Rational Decision-Making with Adaptive Neural Network Priors" is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.

• artificial intelligence
• classification
• clustering
• clustering algorithms
• data security
• feature selection
• image processing
• image segmentation
• learning algorithms
• machine learning
• network architecture
• neural networks
• object recognition
• pattern recognition
• recurrent neural networks
• semantics
• supervised learning
• Support Vector Machines (SVM)

• University of Siena, Siena, Italy

  Luca Pancioni, Edmondo Trentin

• Ulm University, Ulm, Germany

  Friedhelm Schwenker

Policies and ethics