About the book
Nature evolves mainly in a statistical way. Different strategies, formulas, and conformations are continuously confronted in the natural processes. Some of them are selected and then the evolution continues with a new loop of confrontation for the next generation of phenomena and living beings. Failings are corrected without a previous program or design. The new options generated by different statistical and random scenarios lead to solutions for surviving the present conditions. This is the general panorama for all scrutiny levels of the life cycles. In the last years, many methods grounded in theory and experience have been developed through machine learning and computational statistics to approach and simulate this type of behavior. Clustering, supervised and unsupervised learning, parameter optimization, feature selection, visualization techniques, ensemble methods, and evolutionary dynamics try to offer an alternative way for a better predictive performance in proteomics, genetics, spread of viruses, effectiveness and efficiency of vaccines, etc.
The goal of this book is to be useful to an audience interested in and involved with the computational statistics and machine learning applications.