Topography Preserving Gaussian Mixture Models As Cortical Maps

In this thesis two topography preserving Gaussian Mixture Models are used to model cortical maps. Two major novel contributions are presented; the application of the Generative Topographic Mapping (GTM) to the formation of ocular dominance stripes and using the Elastic Net (EN) as a visual category representation. The applications are motivated by Marr's computational framework in that the contributions correspond to different levels of abstraction. Firstly, motivated by theoretical and experimental comparisons of the GTM and EN, the GTM is applied for the formation of ocular dominance stripes. Simulations are presented that demonstrate that the GTM can indeed produce realistic looking patterns in some instances, though careful parameter selection is required. In addition the GTM exhibits properties that the EN does not, such as twisting and 'hyper sensitivity'. Consequently it is proposed that further mathematical investigation may relate the neuronal interoprability of the GTM to that of the EN. In the second application the EN is used to model population of neurons in higher level processing that are postulated to code visual categories. Using the EN visualisations are presented that allow some novel insights. Motivated by the ability of the EN to capture 'high level' concepts a novel visual categorisation scheme is suggested. The proposed system is evaluated on the Caltech101 data set and shows good performance. A number of interesting future directions that pertain to both artificial and biological vision are suggested.

A new perspective on topographic map formation and the advantages of information-based learning The study of topographic map formation provides us with important tools for both biological modeling and statistical data modeling. Faithful Representations and Topographic Maps offers a unified, systematic survey of this rapidly evolving field, focusing on current knowledge and available techniques for topographic map formation. The author presents a cutting-edge, information-based learning strategy for developing equiprobabilistic topographic maps--that is, maps in which all neurons have an equal probability to be active--clearly demonstrating how this approach yields faithful representations and how it can be successfully applied in such areas as density estimation, regression, clustering, and feature extraction. The book begins with the standard approach of distortion-based learning, discussing the commonly used Self-Organizing Map (SOM) algorithm and other algorithms, and pointing out their inadequacy for developing equiprobabilistic maps. It then examines the advantages of information-based learning techniques, and finally introduces a new algorithm for equiprobabilistic topographic map formation using neurons with kernel-based response characteristics. The complete learning algorithms and simulation details are given throughout, along with comparative performance analysis tables and extensive references. Faithful Representations and Topographic Maps is an excellent, eye-opening guide for neural network researchers, industrial scientists involved in data mining, and anyone interested in self-organization and topographic maps.

The proceedings of this workshop include invited lectures by Professors Stan Gielen and Lotfi Zadeh. The workshop was the last to be organised by the late Professor Eduardo R. Cainello, known worldwide for his fundamental contributions to cybernetics and theoretical physics, and to whom this volume is dedicated.

Artificial Intelligence Tools: Decision Support Systems in Condition Monitoring and Diagnosis discusses various white- and black-box approaches to fault diagnosis in condition monitoring (CM). This indispensable resource:Addresses nearest-neighbor-based, clustering-based, statistical, and information theory-based techniquesConsiders the merits of e

Natural Computing is the field of research that investigates both human-designed computing inspired by nature and computing taking place in nature, i.e., it investigates models and computational techniques inspired by nature and also it investigates phenomena taking place in nature in terms of information processing. Examples of the first strand of research covered by the handbook include neural computation inspired by the functioning of the brain; evolutionary computation inspired by Darwinian evolution of species; cellular automata inspired by intercellular communication; swarm intelligence inspired by the behavior of groups of organisms; artificial immune systems inspired by the natural immune system; artificial life systems inspired by the properties of natural life in general; membrane computing inspired by the compartmentalized ways in which cells process information; and amorphous computing inspired by morphogenesis. Other examples of natural-computing paradigms are molecular computing and quantum computing, where the goal is to replace traditional electronic hardware, e.g., by bioware in molecular computing. In molecular computing, data are encoded as biomolecules and then molecular biology tools are used to transform the data, thus performing computations. In quantum computing, one exploits quantum-mechanical phenomena to perform computations and secure communications more efficiently than classical physics and, hence, traditional hardware allows. The second strand of research covered by the handbook, computation taking place in nature, is represented by investigations into, among others, the computational nature of self-assembly, which lies at the core of nanoscience, the computational nature of developmental processes, the computational nature of biochemical reactions, the computational nature of bacterial communication, the computational nature of brain processes, and the systems biology approach to bionetworks where cellular processes are treated in terms of communication and interaction, and, hence, in terms of computation. We are now witnessing exciting interaction between computer science and the natural sciences. While the natural sciences are rapidly absorbing notions, techniques and methodologies intrinsic to information processing, computer science is adapting and extending its traditional notion of computation, and computational techniques, to account for computation taking place in nature around us. Natural Computing is an important catalyst for this two-way interaction, and this handbook is a major record of this important development.

Methods based on neural networks are assuming an increasing role in biomedical research. This book presents an introduction to the application of neural networks and related areas of artificial intelligence to biological structure analysis, biomedical images understanding, electrophysiologic signal analysis and other stimulating issues of biomedicine.This book, which will include the latest advances and developments in the field, will be of value to researchers in neural networks and biomedicine.

This book constitutes the refereed proceedings of the 6th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2005, held in Brisbane, Australia, in July 2005. The 76 revised full papers presented were carefully reviewed and selected from 167 submissions. The papers are organized in topical sections on data mining and knowledge engineering, learning algorithms and systems, bioinformatics, agent technologies, and financial engineering.

The fifth edition of a work that defines the field of cognitive neuroscience, with entirely new material that reflects recent advances in the field. Each edition of this classic reference has proved to be a benchmark in the developing field of cognitive neuroscience. The fifth edition of The Cognitive Neurosciences continues to chart new directions in the study of the biological underpinnings of complex cognition—the relationship between the structural and physiological mechanisms of the nervous system and the psychological reality of the mind. It offers entirely new material, reflecting recent advances in the field. Many of the developments in cognitive neuroscience have been shaped by the introduction of novel tools and methodologies, and a new section is devoted to methods that promise to guide the field into the future—from sophisticated models of causality in brain function to the application of network theory to massive data sets. Another new section treats neuroscience and society, considering some of the moral and political quandaries posed by current neuroscientific methods. Other sections describe, among other things, new research that draws on developmental imaging to study the changing structure and function of the brain over the lifespan; progress in establishing increasingly precise models of memory; research that confirms the study of emotion and social cognition as a core area in cognitive neuroscience; and new findings that cast doubt on the so-called neural correlates of consciousness.

In an age where the amount of data collected from brain imaging is increasing constantly, it is of critical importance to analyse those data within an accepted framework to ensure proper integration and comparison of the information collected. This book describes the ideas and procedures that underlie the analysis of signals produced by the brain. The aim is to understand how the brain works, in terms of its functional architecture and dynamics. This book provides the background and methodology for the analysis of all types of brain imaging data, from functional magnetic resonance imaging to magnetoencephalography. Critically, Statistical Parametric Mapping provides a widely accepted conceptual framework which allows treatment of all these different modalities. This rests on an understanding of the brain's functional anatomy and the way that measured signals are caused experimentally. The book takes the reader from the basic concepts underlying the analysis of neuroimaging data to cutting edge approaches that would be difficult to find in any other source. Critically, the material is presented in an incremental way so that the reader can understand the precedents for each new development. This book will be particularly useful to neuroscientists engaged in any form of brain mapping; who have to contend with the real-world problems of data analysis and understanding the techniques they are using. It is primarily a scientific treatment and a didactic introduction to the analysis of brain imaging data. It can be used as both a textbook for students and scientists starting to use the techniques, as well as a reference for practicing neuroscientists. The book also serves as a companion to the software packages that have been developed for brain imaging data analysis. An essential reference and companion for users of the SPM software Provides a complete description of the concepts and procedures entailed by the analysis of brain images Offers full didactic treatment of the basic mathematics behind the analysis of brain imaging data Stands as a compendium of all the advances in neuroimaging data analysis over the past decade Adopts an easy to understand and incremental approach that takes the reader from basic statistics to state of the art approaches such as Variational Bayes Structured treatment of data analysis issues that links different modalities and models Includes a series of appendices and tutorial-style chapters that makes even the most sophisticated approaches accessible