Last chance! 50% off unlimited learning
Sale ends in
Comon's GAP criterion to evaluate the performance of an ICA algorithm.
ComonGAP(A, A.hat)
The value of the Comon's GAP.
The true square mixing matrix.
The estimated square mixing matrix.
Klaus Nordhausen
Comon's GAP criterion is permutation and scale invariant. It can take every positive value and 0 corresponds to an optimal separation.
If A
is however nearly singular the values of the criterion can be huge.
Note that this function assumes the ICA model is JADE
and ics
. However fastICA
and
PearsonICA
assume
Comon, P., (1994), Independent Component Analysis, A new concept?, Signal Processing, 36, 287--314.
amari.error
, SIR
S <- cbind(rt(1000, 4), rnorm(1000), runif(1000))
A <- matrix(rnorm(9), ncol = 3)
X <- S %*% t(A)
A.hat <- JADE(X, 3)$A
ComonGAP(A, A.hat)
Run the code above in your browser using DataLab