BNNprior: Prior Probability of Bayesian Neural Networks

In BNN: Bayesian Neural Network for High-Dimensional Nonlinear Variable Selection

Description

Calculating the prior probability of linear and nonlinear classes of BNN models.

Usage

BNNprior(dimX, dimY, hid_num = 3,lambda=0.025,total_iteration=1000000,popN = 20)

Arguments

dimX	Dimension of the input data.
dimY	The dimension of reponse data. It is restricted to 1 in the current version of the package.
hid_num	Number of hidden units. The default setting is 3.
lambda	The prior probability for each connection of the neural network being selected for the final model. The default setting is 0.025.
total_iteration	Number of total iterations, default of 1000,000.
popN	Number of Markov Chains, default of 20.

Value

prob	Prior probability assigned to the class of linear models.

Author(s)

Bochao Jia and Faming Liang

References

Liang, F., Li, Q., and Zhou, L. (2017). Bayesian Neural Networks for Selection of Drug Sensitive Genes. Journal of the American Statistical Association.

Examples

library(BNN)
BNNprior(50, 1, hid_num = 3, lambda=0.025, total_iteration = 10000, popN = 5)

BNN documentation built on May 2, 2019, 4:13 a.m.