Kernel Methods

by José Luis Rojo-Alvarez (Author),‎ Manel Marti­nez-Ramon (Author),‎ Jordi Muñoz-Marí (Author),‎ Gustau Camps-Valls (Author)

The development of kernel methods and hybrid evolutionary algorithms (HEAs) to support experts in energy forecasting is of great importance to improving the accuracy of the actions derived from an energy decision maker, and it is crucial that they are theoretically sound. In addition, more accurate or more precise energy demand forecasts are required when decisions are made in a competitive environment. Therefore, this is of special relevance in the Big Data era. These forecasts are usually based on a complex function combination. These models have resulted in over-reliance on the use of informal judgment and higher expense if lacking the ability to catch the data patterns. The novel applications of kernel methods and hybrid evolutionary algorithms can provide more satisfactory parameters in forecasting models.

In the last decade, a number of powerful kernel-based learning methods have been proposed in the machine learning community: support vector machines (SVMs), kernel fisher discriminant (KFD) analysis, kernel PCA/ICA, kernel mutual information, kernel k-means, and kernel ARMA.

Kernel methods have long been established as effective techniques in the framework of machine learning and pattern recognition, and have now become the standard approach to many remote sensing applications.

Offering a fundamental basis in kernel-based learning theory, this book covers both statistical and algebraic principles. It provides over 30 major theorems for kernel-based supervised and unsupervised learning models. The first of the theorems establishes a condition, arguably necessary and sufficient, for the kernelization of learning models.