• Artificial Neural Networks and...

*Result*: Artificial Neural Networks and Deep Learning for Genomic Prediction of Binary, Ordinal, and Mixed Outcomes

Title:
Artificial Neural Networks and Deep Learning for Genomic Prediction of Binary, Ordinal, and Mixed Outcomes
Authors:
Montesinos López, Osval Antonio, Montesinos López, Abelardo, Crossa, Jose
Contributors:
Bill and Melinda Gates Foundation
Source:
Multivariate Statistical Machine Learning Methods for Genomic Prediction ; page 477-532 ; ISBN 9783030890094 9783030890100
Publisher Information:
Springer International Publishing
Publication Year:
2022
Document Type:
*Book* book part
Language:
English
ISBN:
978-3-030-89009-4
978-3-030-89010-0
3-030-89009-0
3-030-89010-4
DOI:
10.1007/978-3-030-89010-0_12
Availability:
http://dx.doi.org/10.1007/978-3-030-89010-0_12
https://link.springer.com/content/pdf/10.1007/978-3-030-89010-0_12
Rights:
https://creativecommons.org/licenses/by/4.0 ; https://creativecommons.org/licenses/by/4.0 ; https://creativecommons.org/licenses/by/4.0 ; https://creativecommons.org/licenses/by/4.0
Accession Number:
edsbas.63A5511
Database:
BASE

*Further Information*

*In this chapter, we provide the main elements for implementing deep neural networks in Keras for binary, categorical, and mixed outcomes under feedforward networks as well as the main practical issues involved in implementing deep learning models with binary response variables. The same practical issues are provided for implementing deep neural networks with categorical and count traits under a univariate framework. We follow with a detailed assessment of information for implementing multivariate deep learning models for continuous, binary, categorical, count, and mixed outcomes. In all the examples given, the data came from plant breeding experiments including genomic data. The training process for binary, ordinal, count, and multivariate outcomes is similar to fitting DNN models with univariate continuous outcomes, since once we have the data to be trained, we need to (a) define the DNN model in Keras, (b) configure and compile the model, (c) fit the model, and finally, (d) evaluate the prediction performance in the testing set. In the next section, we provide illustrative examples of training DNN for binary outcomes in Keras R (Chollet and Allaire, Deep learning with R. Manning Publications, Manning Early Access Program (MEA), 2017; Allaire and Chollet, Keras: R interface to Keras’, 2019).*