CoCalc Public Filesr-neuralnet.htmlOpen with one click!
Authors: harald @schil.ly, Testing CoCalc, Harald Schilly, Harald Schilly, HaraldTest SchillyTest, ℏal Snyder, William A. Stein
Views : 102
Description: Jupyter html version of r-neuralnet.ipynb
Compute Environment: Ubuntu 18.04 (Deprecated)
r-neuralnet

R's Neuralnet

Training of neural networks using backpropagation, resilient backpropagation with (Riedmiller, 1994) or without weight backtracking (Riedmiller and Braun, 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.

https://cran.r-project.org/web/packages/neuralnet/index.html

In [1]:
require(neuralnet)
XOR <- c(0,1,1,0)
xor.data <- data.frame(expand.grid(c(0,1), c(0,1)), XOR)
net.xor <- neuralnet( XOR~Var1+Var2, xor.data, hidden=2, rep=5)
plot(net.xor, rep="best")
Loading required package: neuralnet
In [ ]: