Innovations in Neural Information Paradigms and Applications

1. Front Matter

   PDF

2. Advances in Neural Information Processing Paradigms

   • Monica Bianchini, Marco Maggini, Franco Scarselli, Lakhmi C. Jain

   Pages 1-7

3. Self-Organizing Maps for Structured Domains: Theory, Models, and Learning of Kernels

   • Fabio Aiolli, Giovanni Da San Martino, Markus Hagenbuchner, Alessandro Sperduti

   Pages 9-42

4. Unsupervised and Supervised Learning of Graph Domains

   • A. C. Tsoi, Markus Hagenbuchner, R. Chau, Vincent Lee

   Pages 43-65

5. Neural Grammar Networks

   • Eddie Y. T. Ma, Stefan C. Kremer

   Pages 67-96

6. Estimates of Model Complexity in Neural-Network Learning

   • Věra Kůrková

   Pages 97-111

7. Regularization and Suboptimal Solutions in Learning from Data

   • Giorgio Gnecco, Marcello Sanguineti

   Pages 113-154

8. Probabilistic Interpretation of Neural Networks for the Classification of Vectors, Sequences and Graphs

   • Edmondo Trentin, Antonino Freno

   Pages 155-182

9. Metric Learning for Prototype-Based Classification

   • Michael Biehl, Barbara Hammer, Petra Schneider, Thomas Villmann

   Pages 183-199

10. Bayesian Linear Combination of Neural Networks

    • Battista Biggio, Giorgio Fumera, Fabio Roli

    Pages 201-230

11. Credit Card Transactions, Fraud Detection, and Machine Learning: Modelling Time with LSTM Recurrent Neural Networks

    • Bénard Wiese, Christian Omlin

    Pages 231-268

12. Towards Computational Modelling of Neural Multimodal Integration Based on the Superior Colliculus Concept

    • Kiran Ravulakollu, Michael Knowles, Jindong Liu, Stefan Wermter

    Pages 269-291

13. Back Matter

    PDF

Tremendous advances in all disciplines including engineering, science, health care, business, avionics, management, and so on, can also be attributed to the development of artificial intelligence paradigms. In fact, researchers are always interested in desi- ing machines which can mimic the human behaviour in a limited way. Therefore, the study of neural information processing paradigms have generated great interest among researchers, in that machine learning, borrowing features from human intelligence and applying them as algorithms in a computer friendly way, involves not only Mathem- ics and Computer Science but also Biology, Psychology, Cognition and Philosophy (among many other disciplines). Generally speaking, computers are fundamentally well-suited for performing au- matic computations, based on fixed, programmed rules, i.e. in facing efficiently and reliably monotonous tasks, often extremely time-consuming from a human point of view. Nevertheless, unlike humans, computers have troubles in understanding specific situations, and adapting to new working environments. Artificial intelligence and, in particular, machine learning techniques aim at improving computers behaviour in tackling such complex tasks. On the other hand, humans have an interesting approach to problem-solving, based on abstract thought, high-level deliberative reasoning and pattern recognition. Artificial intelligence can help us understanding this process by recreating it, then potentially enabling us to enhance it beyond our current capabilities.

• Computational Intelligence
• Neural Information Systems
• Neural Network
• information processing
• machine learning
• neural networks
• supervised learning

• Dipartimento di Ingegneria dell’ Informazione, Università degli Studi di Siena, Siena, Italy

  Monica Bianchini, Marco Maggini, Franco Scarselli

• University of South Australia, Australia

  Lakhmi C. Jain

Policies and ethics