The application of a “committee of experts” or ensemble learning to artificial neural networks that apply unsupervised learning techniques is widely considered to enhance the effectiveness of such networks greatly. This book examines the potential of the ensemble meta-algorithm by describing and testing a technique based on the combination of ensembles and statistical PCA that is able to determine the presence of outliers in high-dimensional data sets and to minimize outlier effects in the final results. Its central contribution concerns an algorithm for the ensemble fusion of topology-preserving maps, referred to as Weighted Voting Superposition (WeVoS), which has been devised to improve data exploration by 2-D visualization over multi-dimensional data sets. This generic algorithm is applied in combination with several other models taken from the family of topology preserving maps, such as the SOM, ViSOM, SIM and Max-SIM. A range of quality measures for topology preserving maps that are proposed in the literature are used to validate and compare WeVoS with other algorithms. The experimental results demonstrate that, in the majority of cases, the WeVoS algorithm outperforms earlier map-fusion methods and the simpler versions of the algorithm with which it is compared. All the algorithms are tested in different artificial data sets and in several of the most common machine-learning data sets in order to corroborate their theoretical properties. Moreover, a real-life case-study taken from the food industry demonstrates the practical benefits of their application to more complex problems.

The application of a “committee of experts” or ensemble learning to artificial neural networks that apply unsupervised learning techniques is widely considered to enhance the effectiveness of such networks greatly. This book examines the potential of the ensemble meta-algorithm by describing and testing a technique based on the combination of ensembles and statistical PCA that is able to determine the presence of outliers in high-dimensional data sets and to minimize outlier effects in the final results. Its central contribution concerns an algorithm for the ensemble fusion of topology-preserving maps, referred to as Weighted Voting Superposition (WeVoS), which has been devised to improve data exploration by 2-D visualization over multi-dimensional data sets. This generic algorithm is applied in combination with several other models taken from the family of topology preserving maps, such as the SOM, ViSOM, SIM and Max-SIM. A range of quality measures for topology preserving maps that are proposed in the literature are used to validate and compare WeVoS with other algorithms. The experimental results demonstrate that, in the majority of cases, the WeVoS algorithm outperforms earlier map-fusion methods and the simpler versions of the algorithm with which it is compared. All the algorithms are tested in different artificial data sets and in several of the most common machine-learning data sets in order to corroborate their theoretical properties. Moreover, a real-life case-study taken from the food industry demonstrates the practical benefits of their application to more complex problems.

Data fusion problems arise frequently in many different fields. This book provides a specific introduction to data fusion problems using support vector machines. In the first part, this book begins with a brief survey of additive models and Rayleigh quotient objectives in machine learning, and then introduces kernel fusion as the additive expansion of support vector machines in the dual problem. The second part presents several novel kernel fusion algorithms and some real applications in supervised and unsupervised learning. The last part of the book substantiates the value of the proposed theories and algorithms in MerKator, an open software to identify disease relevant genes based on the integration of heterogeneous genomic data sources in multiple species. The topics presented in this book are meant for researchers or students who use support vector machines. Several topics addressed in the book may also be interesting to computational biologists who want to tackle data fusion challenges in real applications. The background required of the reader is a good knowledge of data mining, machine learning and linear algebra.

This book contains the articles from the international conference 11th Workshop on Self-Organizing Maps 2016 (WSOM 2016), held at Rice University in Houston, Texas, 6-8 January 2016. WSOM is a biennial international conference series starting with WSOM'97 in Helsinki, Finland, under the guidance and direction of Professor Tuevo Kohonen (Emeritus Professor, Academy of Finland). WSOM brings together the state-of-the-art theory and applications in Competitive Learning Neural Networks: SOMs, LVQs and related paradigms of unsupervised and supervised vector quantization.The current proceedings present the expert body of knowledge of 93 authors from 15 countries in 31 peer reviewed contributions. It includes papers and abstracts from the WSOM 2016 invited speakers representing leading researchers in the theory and real-world applications of Self-Organizing Maps and Learning Vector Quantization: Professor Marie Cottrell (Universite Paris 1 Pantheon Sorbonne, France), Professor Pablo Estevez (University of Chile and Millennium Instituteof Astrophysics, Chile), and Professor Risto Miikkulainen (University of Texas at Austin, USA). The book comprises a diverse set of theoretical works on Self-Organizing Maps, Neural Gas, Learning Vector Quantization and related topics, and an excellent variety of applications to data visualization, clustering, classification, language processing, robotic control, planning, and to the analysis of astronomical data, brain images, clinical data, time series, and agricultural data.

This book delivers a definite and compact knowledge on how hybridization can help improving the quality of computer classification systems. In order to make readers clearly realize the knowledge of hybridization, this book primarily focuses on introducing the different levels of hybridization and illuminating what problems we will face with as dealing with such projects. In the first instance the data and knowledge incorporated in hybridization were the action points, and then a still growing up area of classifier systems known as combined classifiers was considered. This book comprises the aforementioned state-of-the-art topics and the latest research results of the author and his team from Department of Systems and Computer Networks, Wroclaw University of Technology, including as classifier based on feature space splitting, one-class classification, imbalance data, and data stream classification.

Computational Methods for the Innovative Design of Electrical Devices is entirely focused on the optimal design of various classes of electrical devices. Emerging new methods, like e.g. those based on genetic algorithms, are presented and applied in the design optimization of different devices and systems. Accordingly, the solution to field analysis problems is based on the use of finite element method, and analytical methods as well. An original aspect of the book is the broad spectrum of applications in the area of electrical engineering, especially electrical machines. This way, traditional design criteria of conventional devices are revisited in a critical way, and some innovative solutions are suggested. In particular, the optimization procedures developed are oriented to three main aspects: shape design, material properties identification, machine optimal behaviour. Topics covered include: • New parallel finite-element solvers • Response surface method • Evolutionary computing • Multiobjective optimization • Swarm intelligence • MEMS applications • Identification of magnetic properties of anisotropic laminations • Neural networks for non-destructive testing • Brushless DC motors, transformers • Permanent magnet disc motors, magnetic separators • Magnetic levitation systems

The three volume set LNCS 7062, LNCS 7063, and LNCS 7064 constitutes the proceedings of the 18th International Conference on Neural Information Processing, ICONIP 2011, held in Shanghai, China, in November 2011. The 262 regular session papers presented were carefully reviewed and selected from numerous submissions. The papers of part I are organized in topical sections on perception, emotion and development, bioinformatics, biologically inspired vision and recognition, bio-medical data analysis, brain signal processing, brain-computer interfaces, brain-like systems, brain-realistic models for learning, memory and embodied cognition, Clifford algebraic neural networks, combining multiple learners, computational advances in bioinformatics, and computational-intelligent human computer interaction. The second volume is structured in topical sections on cybersecurity and data mining workshop, data mining and knowledge doscovery, evolutionary design and optimisation, graphical models, human-originated data analysis and implementation, information retrieval, integrating multiple nature-inspired approaches, Kernel methods and support vector machines, and learning and memory. The third volume contains all the contributions connected with multi-agent systems, natural language processing and intelligent Web information processing, neural encoding and decoding, neural network models, neuromorphic hardware and implementations, object recognition, visual perception modelling, and advances in computational intelligence methods based pattern recognition.