proDSfit: Training of the evidential neural network classifier

Description

proDSfit performs parameter optimization for the evidential neural network classifier.

Usage

proDSfit(
  x,
  y,
  param,
  lambda = 1/max(as.numeric(y)),
  mu = 0,
  optimProto = TRUE,
  options = list(maxiter = 500, eta = 0.1, gain_min = 1e-04, disp = 10)
)

Value

A list with three elements:

param: Optimized network parameters.
cost: Final value of the cost function.
err: Training error rate.

Arguments

x: Input matrix of size n x d, where n is the number of objects and d the number of attributes.
y: Vector of class lables (of length n). May be a factor, or a vector of integers from 1 to M (number of classes).
param: Initial parameters (see link{proDSinit}).
lambda: Parameter of the cost function. If lambda=1, the cost function measures the error between the plausibilities and the 0-1 target values. If lambda=1/M, where M is the number of classes (default), the piginistic probabilities are considered in the cost function. If lambda=0, the beliefs are used.
mu: Regularization hyperparameter (default=0).
optimProto: Boolean. If TRUE, the prototypes are optimized (default). Otherwise, they are fixed.
options: A list of parameters for the optimization algorithm: maxiter (maximum number of iterations), eta (initial step of gradient variation), gain_min (minimum gain in the optimisation loop), disp (integer; if >0, intermediate results are displayed every disp iterations).

Author

Thierry Denoeux.

Details

If optimProto=TRUE (default), the prototypes are optimized. Otherwise, they are fixed to their initial value.

References

T. Denoeux. A neural network classifier based on Dempster-Shafer theory. IEEE Trans. on Systems, Man and Cybernetics A, 30(2):131--150, 2000.

Examples

Run this code

## Glass dataset
data(glass)
xapp<-glass$x[1:89,]
yapp<-glass$y[1:89]
xtst<-glass$x[90:185,]
ytst<-glass$y[90:185]
## Initialization
param0<-proDSinit(xapp,yapp,nproto=7)
## Training
fit<-proDSfit(xapp,yapp,param0)

Run the code above in your browser using DataLab