neuralnet: Training of Neural Networks

neuralnet: Обучение нейронных сетей
Frauke Günther, Stefan Gerd Fritsch
2010-01-01

R packagebackpropagationcustom activation functioncustom error functioninfert datasetmultilayer perceptronneuralnetregression analysisresilient backpropagation
Artificial neural networks are applied in many situations.neuralnet is built to train multi-layer perceptrons in the context of regression analyses, i.e. to approximate functional relationships between covariates and response variables.Thus, neural networks are used as extensions of generalized linear models.neuralnet is a very flexible package.The backpropagation algorithm and three versions of resilient backpropagation are implemented and it provides a custom-choice of activation and error function.An arbitrary number of covariates and response variables as well as of hidden layers can theoretically be included.The paper gives a brief introduction to multilayer perceptrons and resilient backpropagation and demonstrates the application of neuralnet using the data set infert, which is contained in the R distribution.
1
The paper demonstrates neuralnet usage on the R dataset 'infert' and provides introductions to MLPs and resilient backpropagation.
2
neuralnet allows custom choice of activation and error functions.
3
neuralnet implements backpropagation and three versions of resilient backpropagation as training algorithms.
4
neuralnet package trains multi-layer perceptrons for regression to approximate relationships between covariates and responses.
5
neuralnet supports an arbitrary number of covariates, response variables, and hidden layers in theory.

neuralnet R package for training multilayer perceptrons

Training and configuration of artificial neural networks for regression (implementation of backpropagation and resilient backpropagation variants, activation/error function choices, and network architecture) to approximate relationships between covariates and response variables

Publication Details
Publication Date
2010-01-01
Journal
Publisher
ISSN
Cited by
757
Access Type
Author Information
Authors
Frauke Günther
Stefan Gerd Fritsch
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%