Alogorithmic Learning in a Random World,
V. Vovk, A.Gammerman and G. Shafer, 2005
Conformal predictions, the main topic of this monograph, is an exciting new method of machine learning. Conformal predictors are among the most accurate methods of machine learning, and unlike other sate-of-the-art methods, they provide information about their own accuracy and reliability.
The monograph includes a rigorous mathematical theory and careful experimental work. It demonstrates mathematically the validity of the reliability claimed by conformal predictors when they are applied to independent and identically distributed data, and it confirms experimentally that the accuracy is sufficient for many practical problems. Later chapters of the monograph generalize these results from independent and identically distributed data to models called repetitive structures, which originate in the algorithmic theory of randomness and statistical physics. The approach is flexible enough to incorporate most existing methods of machine learning, including newer methods such as boosting and support vector machines and older methods such as nearest neighbours and the bootstrap.
Topics and features:
- Describes how conformal predictors yield accurate and reliable predictions complemented with quantatitive measures of their accuracy and reliability.
- Gives equal attention to classification and regression problems.
- Explains how to apply the new algorithms to real-world data sets.
- Explains connections with Kolmogorov's algorithmic randomness, recent work in machine learning, and older work in statistics.
- Develops new methods of probability forecasting and shows how to use them for prediction in causal networks.
- Researchers in computer science, statistics, and artificial intelligence will find the book an authoritative and rigorous treatment of some of the most promising new developments in machine learning. Practitioners and students in all areas of research that use statistical prediction or machine learning will find exciting new methods.
ISBN: 0-387-00152-2
Tel/Fax : +44 (0)1784 443421 /439786