This matrix was calculated by using the dominance incidence matrix derived from 33,267 Single Nucleotide
Polymorphisms (SNPs) information on 297 individually cows,
$$D=\frac{X_d X_d'}{2 \sum_{j=1}^p (p_j^2+q_j^2) p_j q_j},$$
where
<ul>
<li>$X_d$ is the design matrix for allele substitution effects for dominance.</li>
<li>$p_j$ is the frecuency of the second allele at locus $j$ and $q_j=1-p_j$.</li>
</ul>

datasets

Bayesian regularization for feed-forward neural networks.

Paulino Rodriguez

brnn

Bayesian Regularization for Feed-Forward Neural Networks

D function

This matrix was calculated by using the dominance incidence matrix derived from 33,267 Single Nucleotide
Polymorphisms (SNPs) information on 297 individually cows,
$$D=\frac{X_d X_d'}{2 \sum_{j=1}^p (p_j^2+q_j^2) p_j q_j},$$
where
<ul>
<li>$X_d$ is the design matrix for allele substitution effects for dominance.</li>
<li>$p_j$ is the frecuency of the second allele at locus $j$ and $q_j=1-p_j$.</li>
</ul>

D: Genomic dominant relationship matrix for the Jersey dataset.

Description

Arguments