neuralnet-package {neuralnet}

Training of Neural Networks

Description

Training of neural networks using the backpropagation, resilient backpropagation with (Riedmiller, 1994) or without weight backtracking (Riedmiller, 1993) or the modified globally convergent version by Anastasiadis et al. (2005). The package allows flexible settings through custom-choice of error and activation function. Furthermore, the calculation of generalized weights (Intrator O & Intrator N, 1993) is implemented.

Note

This work has been supported by the German Research Foundation
(DFG: http://www.dfg.de) under grant scheme PI 345/3-1.

Author(s)

Stefan Fritsch, Frauke Guenther [e-mail],

Maintainer: Frauke Guenther [e-mail]

References

Riedmiller M. (1994) Rprop - Description and Implementation Details. Technical Report. University of Karlsruhe.

Riedmiller M. and Braun H. (1993) A direct adaptive method for faster backpropagation learning: The RPROP algorithm. Proceedings of the IEEE International Conference on Neural Networks (ICNN), pages 586-591. San Francisco.

Anastasiadis A. et. al. (2005) New globally convergent training scheme based on the resilient propagation algorithm. Neurocomputing 64, pages 253-270.

Intrator O. and Intrator N. (1993) Using Neural Nets for Interpretation of Nonlinear Models. Proceedings of the Statistical Computing Section, 244-249 San Francisco: American Statistical Society (eds).

See Also

plot.nn for plotting of the neural network.

gwplot for plotting of the generalized weights.

compute for computation of the calculated network.

confidence.interval for calculation of a confidence interval for the weights.

prediction for calculation of a prediction.

Examples

AND <- c(rep(0,7),1)
OR <- c(0,rep(1,7))
binary.data <- data.frame(expand.grid(c(0,1), c(0,1), c(0,1)), AND, OR)
print(net <- neuralnet(AND+OR~Var1+Var2+Var3,  binary.data, hidden=0, 
             rep=10, err.fct="ce", linear.output=FALSE))

XOR <- c(0,1,1,0)
xor.data <- data.frame(expand.grid(c(0,1), c(0,1)), XOR)
print(net.xor <- neuralnet(XOR~Var1+Var2, xor.data, hidden=2, rep=5))
plot(net.xor, rep="best")

data(infert, package="datasets")
print(net.infert <- neuralnet(case~parity+induced+spontaneous,  infert, 
                    err.fct="ce", linear.output=FALSE, likelihood=TRUE))
gwplot(net.infert, selected.covariate="parity")
gwplot(net.infert, selected.covariate="induced")
gwplot(net.infert, selected.covariate="spontaneous")
confidence.interval(net.infert)

Var1 <- runif(50, 0, 100) 
sqrt.data <- data.frame(Var1, Sqrt=sqrt(Var1))
print(net.sqrt <- neuralnet(Sqrt~Var1, sqrt.data, hidden=10, 
                  threshold=0.01))
predict(net.sqrt, data.frame(Var1 = (1:10)^2))

Var1 <- rpois(100,0.5)
Var2 <- rbinom(100,2,0.6)
Var3 <- rbinom(100,1,0.5)
SUM <- as.integer(abs(Var1+Var2+Var3+(rnorm(100))))
sum.data <- data.frame(Var1,Var2,Var3, SUM)
print(net.sum <- neuralnet(SUM~Var1+Var2+Var3, sum.data, hidden=1, 
                 act.fct="tanh"))
prediction(net.sum)