neuralnet: Training of Neural Networks

Artificial neural networks are applied in many situations. neuralnet is built to train multi-layer perceptrons in the context of regres- sion analyses, i.e. to approximate functional rela- tionships between covariates and response vari- ables. Thus, neural networks are used as exten- sions of generalized linear models. neuralnet is a very flexible package. The back- propagation algorithm and three versions of re- silient backpropagation are implemented and it provides a custom-choice of activation and er- ror function. An arbitrary number of covariates and response variables as well as of hidden lay- ers can theoretically be included. The paper gives a brief introduction to multi- layer perceptrons and resilient backpropagation and demonstrates the application of neuralnet using the data set infert, which is contained in the R distribution.

[1]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[2]  Martyn Plummer,et al.  The R Journal , 2012 .

[3]  UK,et al.  Modelling the dusty universe – I. Introducing the artificial neural network and first applications to luminosity and colour distributions , 2009, 0906.3522.

[4]  Eric R. Ziegel,et al.  Generalized Linear Models , 2002, Technometrics.

[5]  Karin Bammann,et al.  Neural networks for modeling gene-gene interactions in association studies , 2009, BMC Genetics.

[6]  D. Trichopoulos,et al.  INDUCED ABORTION AND SECONDARY INFERTILITY , 1976, British journal of obstetrics and gynaecology.

[7]  David Zhang,et al.  Personal recognition using hand shape and texture , 2006, IEEE Transactions on Image Processing.

[8]  Wolfram Schiffmann,et al.  Optimization of the Backpropagation Algorithm for Training Multilayer Perceptrons , 1994 .

[9]  Nathan Intrator,et al.  Interpreting neural-network results: a simulation study , 2001 .

[10]  Christina Gloeckner,et al.  Modern Applied Statistics With S , 2003 .

[11]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[12]  Martin A. Riedmiller,et al.  Advanced supervised learning in multi-layer perceptrons — From backpropagation to adaptive learning algorithms , 1994 .

[13]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[14]  Halbert White,et al.  Learning in Artificial Neural Networks: A Statistical Perspective , 1989, Neural Computation.

[15]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[16]  George D. Magoulas,et al.  New globally convergent training scheme based on the resilient propagation algorithm , 2005, Neurocomputing.

[17]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[18]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[19]  José Neves,et al.  Evolutionary Neural Network Learning , 2003, EPIA.