TY - BOOK AU - Bianchini,Monica AU - Maggini,Marco AU - Scarselli,Franco AU - Jain,Lakhmi C. ED - SpringerLink (Online service) TI - Innovations in Neural Information Paradigms and Applications T2 - Studies in Computational Intelligence, SN - 9783642040030 AV - TA329-348 U1 - 519 23 PY - 2009/// CY - Berlin, Heidelberg PB - Springer Berlin Heidelberg KW - Engineering KW - Artificial intelligence KW - Engineering mathematics KW - Appl.Mathematics/Computational Methods of Engineering KW - Artificial Intelligence (incl. Robotics) N1 - Advances in Neural Information Processing Paradigms -- Self-Organizing Maps for Structured Domains: Theory, Models, and Learning of Kernels -- Unsupervised and Supervised Learning of Graph Domains -- Neural Grammar Networks -- Estimates of Model Complexity in Neural-Network Learning -- Regularization and Suboptimal Solutions in Learning from Data -- Probabilistic Interpretation of Neural Networks for the Classification of Vectors, Sequences and Graphs -- Metric Learning for Prototype-Based Classification -- Bayesian Linear Combination of Neural Networks -- Credit Card Transactions, Fraud Detection, and Machine Learning: Modelling Time with LSTM Recurrent Neural Networks -- Towards Computational Modelling of Neural Multimodal Integration Based on the Superior Colliculus Concept N2 - This research book presents some of the most recent advances in neural information processing models including both theoretical concepts and practical applications. The contributions include: Advances in neural information processing paradigms Self organising structures Unsupervised and supervised learning of graph domains Neural grammar networks Model complexity in neural network learning Regularization and suboptimal solutions in neural learning Neural networks for the classification of vectors, sequences and graphs Metric learning for prototype-based classification Ensembles of neural networks Fraud detection using machine learning Computational modelling of neural multimodal integration This book is directed to the researchers, graduate students, professors and practitioner interested in recent advances in neural information processing paradigms and applications UR - http://dx.doi.org/10.1007/978-3-642-04003-0 ER -