Maximum Entropy And Bayesian Methods: Cambridge, England, 1994 Proceedings Of The Fourteenth International Workshop On Maximum Entropy And Bayesian Methods (fundamental Theories Of Physics)

This volume records papers given at the fourteenth international maximum entropy conference, held at St John's College Cambridge, England. It seems hard to believe that just thirteen years have passed since the first in the series, held at the University of Wyoming in 1981, and six years have passed since the meeting last took place here in Cambridge. So much has happened. There are two major themes at these meetings, inference and physics. The inference work uses the confluence of Bayesian and maximum entropy ideas to develop and explore a wide range of scientific applications, mostly concerning data analysis in one form or another. The physics work uses maximum entropy ideas to explore the thermodynamic world of macroscopic phenomena. Of the two, physics has the deeper historical roots, and much of the inspiration behind the inference work derives from physics. Yet it is no accident that most of the papers at these meetings are on the inference side. To develop new physics, one must use one's brains alone. To develop inference, computers are used as well, so that the stunning advances in computational power render the field open to rapid advance. Indeed, we have seen a revolution. In the larger world of statistics beyond the maximum entropy movement as such, there is now an explosion of work in Bayesian methods, as the inherent superiority of a defensible and consistent logical structure becomes increasingly apparent in practice. Front Matter....Pages i-xi Flow and Diffusion Images from Bayesian Spectral Analysis of Motion-Encoded NMR Data....Pages 1-12 Bayesian Estimation of MR Images from Incomplete Raw Data....Pages 13-22 Quantified Maximum Entropy and Biological EPR Spectra....Pages 23-30 The Vital Importance of Prior Information for the Decomposition of Ion Scattering Spectroscopy Data....Pages 31-40 Bayesian Consideration of the Tomography Problem....Pages 41-49 Using MaxEnt to Determine Nuclear Level Densities....Pages 51-58 A Fresh Look at Model Selection in Inverse Scaterring....Pages 59-67 The Maximum-Entropy Method in Small-Angle Scattering....Pages 69-78 Maximum Entropy Multi-Resolution EM Tomography by Adaptive Subdivision....Pages 79-89 High Resolution Image Construction from IRAS Survey — Parallelization and Artifact Suppression....Pages 91-99 Maximum Entropy Performance Analysis Of Spread-Spectrum Multiple-Access Communications....Pages 101-108 Noise Analysis in Optical Fibre Sensing: A Study using the Maximum Entropy Method....Pages 109-116 Autoclass — A Bayesian Approach to Classification....Pages 117-126 Evolution Review Of BayesCalc, A Mathematica TM Package for doing Bayesian Calculations....Pages 127-134 Bayesian Inference for Basis Function Selection in Nonlinear System Identification using Genetic Algorithms....Pages 135-142 The meaning of the word “Probability”....Pages 143-155 The Hard Truth....Pages 157-164 Are the Samples Doped — If so, How Much?....Pages 165-174 Confidence Intervals from one Observation....Pages 175-182 Hyothesis Refinement....Pages 183-188 Bayesian Density Estimation....Pages 189-198 Scale Invariant Markov Models for Bayesian Inversion of Linear Inverse Problems....Pages 199-212 Foundations: Indifference, Independence & MaxEnt....Pages 213-222 The Maximum Entropy on the Mean Method, Noise and Sensitivity....Pages 223-232 The Maximum Entropy Algorithm Applied to the Two-Dimensional Random Packing Problem....Pages 233-238 Bayesian Comparison of Models for Images....Pages 239-248 Interpolation Models with Multiple Hyperparameters....Pages 249-257 Density Networks and their Application to Protein Modelling....Pages 259-268 The Cluster Expansion: A Hierarchical Density Model....Pages 269-278 The Partitioned Mixture Distribution: Multiple Overlapping Density Models....Pages 279-286 Generating Functional for the BBGKY Hierarchy and the N-Identical-Body Problem....Pages 287-301 Entropies for Continua: Fluids and Magnetofluids....Pages 303-314 A Logical Foundation for Real Thermodynamics....Pages 315-320 Back Matter....Pages 321-323 This Volume Records The Proceedings Of The Fourteenth International Workshop On Maximum Entropy And Bayesian Methods, Held In Cambridge, England From August 1-5, 1994. Throughout Applied Science, Bayesian Inference Is Giving High Quality Results Augmented With Reliabilities In The Form Of Probability Values And Probabilistic Error Bars. Maximum Entropy, With Its Emphasis On Optimally Selected Results, Is An Important Part Of This. Across Wide Areas Of Spectroscopy And Imagery, It Is Now Realistic To Generate Clear Results With Quantified Reliability. This Power Is Underpinned With A Foundation Of Solid Mathematics. The Annual Maximum Entropy Workshops Have Become The Principal Focus Of Developments In The Field, And Which Capture The Imaginative Research That Defines The State Of The Art In The Subject. The Breadth Of Application Is Seen In The Thirty-three Papers Reproduced Here, Which Are Classified Into Subsections On Basics, Applications, Physics And Neural Networks. Audience: This Volume Will Be Of Interest To Graduate Students And Researchers Whose Work Involves Probability Theory, Neural Networks, Spectroscopic Methods, Statistical Thermodynamics And Image Processing. Edited By John Skilling, Sibusiso Sibisi.