sym.nnet: Symbolic neural networks regression
In PROMiDAT/RSDA: R to Symbolic Data Analysis

sym.nnet

R Documentation

Symbolic neural networks regression

Description

Symbolic neural networks regression

Usage

sym.nnet(
  formula,
  sym.data,
  method = c("cm", "crm"),
  hidden = c(10),
  threshold = 0.05,
  stepmax = 1e+05
)

Arguments

`formula`	a symbolic description of the model to be fitted.
`sym.data`	symbolic data.table
`method`	cm crm
`hidden`	a vector of integers specifying the number of hidden neurons (vertices) in each layer.
`threshold`	a numeric value specifying the threshold for the partial derivatives of the error function as stopping criteria.
`stepmax`	the maximum steps for the training of the neural network. Reaching this maximum leads to a stop of the neural network's training process.

References

Lima-Neto, E.A., De Carvalho, F.A.T., (2008). Centre and range method to fitting a linear regression model on symbolic interval data. Computational Statistics and Data Analysis52, 1500-1515

Lima-Neto, E.A., De Carvalho, F.A.T., (2010). Constrained linear regression models for symbolic interval-valued variables. Computational Statistics and Data Analysis 54, 333-347

Lima Neto, E.d.A., de Carvalho, F.d.A.T. Nonlinear regression applied to interval-valued data. Pattern Anal Applic 20, 809–824 (2017). https://doi.org/10.1007/s10044-016-0538-y

Rodriguez, O. (2018). Shrinkage linear regression for symbolic interval-valued variables.Journal MODULAD 2018, vol. Modulad 45, pp.19-38

PROMiDAT/RSDA documentation built on Sept. 14, 2023, 9:16 p.m.