The process of inductive inference -- to infer general laws andprinciples from particular instances -- is the basis of statistical modeling, pattern recognition, and machine learning. The Minimum Descriptive Length (MDL)principle, a powerful method of inductive inference, holds that the bestexplanation, given a limited set of observed data, is the one that permits thegreatest compression of the data -- that the more we are able to compress the data, the more we learn about the regularities underlying the data. Advances in MinimumDescription Length is a sourcebook that will introduce the scientific community tothe foundations of MDL, recent theoretical advances, and practical applications.Thebook begins with an extensive tutorial on MDL, covering its theoreticalunderpinnings, practical implications as well as its various interpretations, andits underlying philosophy. The tutorial includes a brief history of MDL -- from itsroots in the notion of Kolmogorov complexity to the beginning of MDL proper. Thebook then presents recent theoretical advances, introducing modern MDL methods in away that is accessible to readers from many different scientific fields. The bookconcludes with examples of how to apply MDL in research settings that range frombioinformatics and machine learning to psychology.
The process of inductive inference -- to infer general laws andprinciples from particular instances -- is the basis of statistical modeling, pattern recognition, and machine learning. The Minimum Descriptive Length (MDL)principle, a powerful method of inductive inference, holds that the bestexplanation, given a limited set of observed data, is the one that permits thegreatest compression of the data -- that the more we are able to compress the data, the more we learn about the regularities underlying the data. Advances in MinimumDescription Length is a sourcebook that will introduce the scientific community tothe foundations of MDL, recent theoretical advances, and practical applications.Thebook begins with an extensive tutorial on MDL, covering its theoreticalunderpinnings, practical implications as well as its various interpretations, andits underlying philosophy. The tutorial includes a brief history of MDL -- from itsroots in the notion of Kolmogorov complexity to the beginning of MDL proper. Thebook then presents recent theoretical advances, introducing modern MDL methods in away that is accessible to readers from many different scientific fields. The bookconcludes with examples of how to apply MDL in research settings that range frombioinformatics and machine learning to psychology.
Receive great offers and updates
