Multivariate Statistical Machine Learning Methods for Genomic Prediction - Crossa, José

Biographie:
Josafhat Salinas Ruiz holds BS in Agro-industrial Engineering from Universidad Aut?noma Chapingo, Mexico, Masters in Statistics from Colegio de Postgraduados of M?xico and PhD in Biometry from the University of Nebraska-Lincoln, USA. Josafhat Salinas-Ru?z is currently a Professor of Statistics, Multivariate statistics, and Experimental Designs at Colegio de Postgraduados campus C?rdoba, Mexico. His areas of interest include advanced statistical modeling in plant sciences, agriculture, and agronomy, generalized linear mixed models, multivariate analysis and experimental designs. Osval Antonio Montesinos L?pez holds a BS in Agro-industrial Engineering from Universidad Aut?noma Chapingo of M?xico, Masters in Statistics from Colegio de Postgraduados of M?xico and PhD in Statistics and Biometry from the University of Nebraska-Lincoln. Osval A. Montesinos-L?pez is currently a Professor of Statistics, Probability and Statistical Learning at the University of Colima, M?xico. His areas of interest include the development of novel genomic prediction models for plant breeding, high-dimensional data analysis, generalized linear mixed models and Bayesian analysis, multivariate analysis, and experimental designs. He has contributed univariate and multivariate genomic prediction models for predicting breeding values in plants with normal, binary, count and ordinal phenotypes. He also has taught courses on genomic prediction, statistical and machine learning in Mexico, the United States of America, Brazil, Peru, Nigeria, France and India. Jos? Crossa holds a BS in Agriculture from Republic University of Uruguay and a PhD in Statistics and Quantitative Genetics from the University of Nebraska-Lincoln. He has helped define key methodologies for conserving and using the center's maize genetic resources, covering proper regeneration procedures and strategies for forming core subsets of large germplasm collections. Crossa's became Head of the Biometrics and Statistics Unit of CIMMYT and developed theoretical and practical work on genetic resources conservation that made him to be selected the best scientist of the CGIAR Centers in 2008. His substantive body of research and publications has addressed many other areas of breeding and agronomy research, including developing new statistical models for genotype x environment, and QTL x environment interactions, general breeding and experimental design, hybrids and heterotic patterns, and association mapping, to name a few important subjects, and enjoys international acclaim and application. Crossa was given the Distinguish Scientist recognition in CIMMYT and is a Fellow of the Agronomy Society of America and of the Crop Science Society of America, Member of the Mexican Academy of Science, Member of the National Research System of the National Council of Research and Technology (CONACYT) of Mexico, invited professor at Universities in Mexico and Uruguay, and Adjunct Professor at the University of Nebraska. Recently, Crossa and colleges impacted plant breeding by being one of the first researchers in showing genomic-enabled predictions models with high accuracy using pedigree and markers information applied in massive maize and wheat field data....

Sommaire:
Preface.- Chapter 1.- General elements of genomic selection and statistical learning.- Chapter. 2.-?Preprocessing tools for data preparation.- Chapter. 3.-?Elements for building supervised statistical machine learning models.- Chapter. 4.-?Overfitting, model tuning and evaluation of prediction performance.- Chapter. 5.-?Linear Mixed Models.- Chapter. 6.-?Bayesian Genomic Linear Regression.- Chapter. 7.-?Bayesian and classical prediction models for categorical and count data.- Chapter. 8.-?Reproducing Kernel Hilbert Spaces Regression and Classification Methods.- Chapter. 9.-?Support vector machines and support vector regression.- Chapter. 10.-?Fundamentals of artificial neural networks and deep learning.- Chapter. 11.-?Artificial neural networks and deep learning for genomic prediction of continuous outcomes.- Chapter. 12.-?Artificial neural networks and deep learning for genomic prediction of binary, ordinal and mixed outcomes.- Chapter. 13.-?Convolutional neural networks.- Chapter. 14.-?Functional regression.- Chapter. 15.-?Random forest for genomic prediction.