Tenascin, a recently characterized extracellular matrix (ECM) protein which is expressed during embryonic and fetal development, wound healing and various benign and malignant tumors (but highly restricted in normal adult tissues) is believed to affect a number of cellular functions such as cellular growth, differentiation, adhesion and motility. It has been extensively studied in recent years to elucidate cellular phenomena that are associated with development, tissue regeneration and neoplastic growth and behavior. It may be a potential target in the treatment of cancers and other disorders. This book focuses mainly on tissue expression and the poorly known biological role of this ECM protein.

Sequential behavior is essential to intelligence in general and a fundamental part of human activities, ranging from reasoning to language, and from everyday skills to complex problem solving. Sequence learning is an important component of learning in many tasks and application fields: planning, reasoning, robotics natural language processing, speech recognition, adaptive control, time series prediction, financial engineering, DNA sequencing, and so on. This book presents coherently integrated chapters by leading authorities and assesses the state of the art in sequence learning by introducing essential models and algorithms and by examining a variety of applications. The book offers topical sections on sequence clustering and learning with Markov models, sequence prediction and recognition with neural networks, sequence discovery with symbolic methods, sequential decision making, biologically inspired sequence learning models.

This is Volume II of a three volume set constituting the refereed proceedings of the Third International Symposium on Neural Networks, ISNN 2006. 616 revised papers are organized in topical sections on neurobiological analysis, theoretical analysis, neurodynamic optimization, learning algorithms, model design, kernel methods, data preprocessing, pattern classification, computer vision, image and signal processing, system modeling, robotic systems, transportation systems, communication networks, information security, fault detection, financial analysis, bioinformatics, biomedical and industrial applications, and more.

This book constitutes the refereed proceedings of the 10th International Workshop on Structural and Syntactic Pattern Recognition, SSPR 2004 and the 5th International Workshop on Statistical Techniques in Pattern Recognition, SPR 2004, held jointly in Lisbon, Portugal, in August 2004. The 59 revised full papers and 64 revised poster papers presented together with 4 invited papers were carefully reviewed and selected from 219 submissions. The papers are organized in topical sections on graphs; visual recognition and detection; contours, lines, and paths; matching and superposition; transduction and translation; image and video analysis; syntactics, languages, and strings; human shape and action; sequences and graphs; pattern matching and classification; document image analysis; shape analysis; multiple classifier systems; density estimation; clustering; feature selection; classification; and representation.

This book is the first of a two-volume set that constitutes the refereed proceedings of the 17th International Conference on Artificial Neural Networks, ICANN 2007, held in Porto, Portugal, September 2007. Coverage includes advances in neural network learning methods, advances in neural network architectures, neural dynamics and complex systems, data analysis, evolutionary computing, agents learning, as well as temporal synchronization and nonlinear dynamics in neural networks.

This proceedings book showcases the latest research work presented at the Second Edition of the Mediterranean Symposium on Smart City Application (SCAMS 2017), which was held in Tangier, Morocco on October 15–27, 2017. It presents original research results, new ideas and practical development experiences that concentrate on both theory and practice. It includes papers from all areas of Smart City Applications, e.g. Smart Mobility, Big Data, Smart Grids, Smart Homes and Buildings, clouds, crowds, mashups, social networks, and security issues. The conference stimulated cutting-edge research discussions among pioneering researchers, scientists, industrial engineers, and students from all around the world. The topics covered in this book also focus on innovative issues at the international level by bringing together experts from different countries. The scope of SCAMS 2017 included methods and practices that combine various emerging internetworking and data technologies to capture, integrate, analyze, mine, annotate, and visualize data in a meaningful and collaborative manner. A series of international workshops were organized as invited sessions during the SCAMS 2017:The 2nd International Workshop on Smart Learning & Innovative EducationsThe 1st International Workshop on Smart HealthcareThe 1st International Workshop on Mathematics for Smart CityThe 1st International Workshop Industry 4.0 and Smart Manufacturing

Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated- including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Finally, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively.

This is a uniquely comprehensive reference that summarizes the state of the art of signal processing theory and techniques for solving emerging problems in neuroscience, and which clearly presents new theory, algorithms, software and hardware tools that are specifically tailored to the nature of the neurobiological environment. It gives a broad overview of the basic principles, theories and methods in statistical signal processing for basic and applied neuroscience problems.Written by experts in the field, the book is an ideal reference for researchers working in the field of neural engineering, neural interface, computational neuroscience, neuroinformatics, neuropsychology and neural physiology. By giving a broad overview of the basic principles, theories and methods, it is also an ideal introduction to statistical signal processing in neuroscience. - A comprehensive overview of the specific problems in neuroscience that require application of existing and development of new theory, techniques, and technology by the signal processing community - Contains state-of-the-art signal processing, information theory, and machine learning algorithms and techniques for neuroscience research - Presents quantitative and information-driven science that has been, or can be, applied to basic and translational neuroscience problems

This authoritative work provides an in-depth treatment of state space methods, with a range of applications in neural and clinical data. Advanced and state-of-the-art research topics are detailed, including topics in state space analyses, maximum likelihood methods, variational Bayes, sequential Monte Carlo, Markov chain Monte Carlo, nonparametric Bayesian, and deep learning methods. Details are provided on practical applications in neural and clinical data, whether this is characterising time series data from neural spike trains recorded from the rat hippocampus, the primate motor cortex, or the human EEG, MEG or fMRI, or physiological measurements of heartbeats or blood pressures. With real-world case studies of neuroscience experiments and clinical data sets, and written by expert authors from across the field, this is an ideal resource for anyone working in neuroscience and physiological data analysis.