Book Shelf Bioinformatics: The Machine Learning Approach by Pierre Baldi and Soren Brunak, A Bradford Book, 360 pages, $40, ISBN 0-262-02442-X A wealth of data is being generated by genome sequencing projects and other experimental efforts to determine the structure and function of biological molecules. The demands and opportunities for interpreting these data are expanding more than ever. Bioinformatics is the development and application of computer methods for analysis, interpretation and prediction, as well as for the design of experiments. It has emerged as a strategic frontier between biology and computer science. Machine learning approaches (e.g., neural networks, hidden Markov models and belief networks) are ideally suited for areas where there is a lot of data but little theory and this is exactly the situation in molecular biology. As with its predecessor statistical model fitting the goal in machine learning is to extract useful information from a body of data by building good probabilistic models. The particular twist behind machine learning, however, is to automate the process as much as possible. In this book, the authors present the key machine learning approaches and apply them to the computational problems encountered in the analysis of biological data. Baldi is with Net-ID, and Brunak is with the Technical University
of Denmark.
This book is aimed at knowledge workers in business, finance, management and socio-economic sciences. It provides a guide to and techniques for forecasting, decision making, conclusions and evaluations in an environment involving uncertainty, vagueness and impression. Traditional modeling techniques do not capture the nature of complex systems, especially when humans are involved. Fuzzy logic provides effective tools for dealing with such systems. The book emphasizes applications presented in case studies, including time forecasting form project management, new product pricing, client financial risk tolerance policy, deviation and potential problem analysis, inventory control model, stock market strategy. George Bojadziev is with Simon Fraser University, and Maria
Bojadziev is with British Columbia Institute of Technology.
Volume 4 of this series (the first three volumes cover Language, Visual Cognition and Thinking) spans many areas of cognitive science: AI, neural network models, animal cognition, signal detection theory, computational models, reaction-time methods, and cognitive neuroscience. The volume also offers introductions to several general methods and theoretical approaches for analyzing the mind, and shows how some of these approaches are applied in the development of quantitative models. Rather than general and inevitably superficial surveys of areas, the contributors present case studies detailed accounts of one or two achievements within an area. Scarborough is with Brooklyn College, CUNY, and Sternberg is with
the University of Pennsylvania. |