Scientific Applications of Neural Nets

Neural-network models for event analysis are widely used in experimental high-energy physics, star/galaxy discrimination, control of adaptive optical systems, prediction of nuclear properties, fast interpolation of potential energy surfaces in chemistry, classification of mass spectra of organic compounds, protein-structure prediction, analysis of DNA sequences, and design of pharmaceuticals. This book, devoted to this highly interdisciplinary research area, addresses scientists and graduate students. The pedagogically written review articles range over a variety of fields including astronomy, nuclear physics, experimental particle physics, bioinformatics, linguistics, and information processing.

Neural-network models are used in a variety of fields ranging from physics to biology and information processing The articles presented in this book give a thorough overview of the state of the art Includes supplementary material: sn.pub/extras

Inhalt
Neural networks: New tools for modelling and data analysis in science.- Adaptive optics: Neural network wavefront sensing, reconstruction, and prediction.- Nuclear physics with neural networks.- Using neural networks to learn energy corrections in hadronic calorimeters.- Neural networks for protein structure prediction.- Evolution teaches neural networks to predict protein structure.- An application of artificial neural networks in linguistics.- Optimization with neural networks.- Dynamics of networks and applications.