The purpose of this project is to verify the convergence of the training algorithms provided in 69 Neural Network R packages available on CRAN to date. Neural networks must be trained with second order algorithms and not with first order algorithms as many packages seem to do.

Due to the large number of packages to validate, the work has been split among two students. Being Student 1, I will validate 35 packages and prepare the communication for one new task view and websites including, but not limited to, Rpubs and R-bloggers.

At the end of the program, a package will be made available to Neural Network package authors and maintainers to verify and test new algorithms by themselves.


Akshaj Verma


  • Christophe Dutang
  • John Nash
  • Patrice Kiener