verne.freenode.net changed the topic of #mlpack to: http://www.mlpack.org/ -- We don't respond instantly... but we will respond. Give it a few minutes. Or hours. -- Channel logs: http://www.mlpack.org/irc/
curiousguy13 has quit [Ping timeout: 256 seconds]
curiousguy13 has joined #mlpack
govg has quit [Ping timeout: 272 seconds]
vedhu63w has joined #mlpack
decltypeme has joined #mlpack
curiousguy13 has quit [Ping timeout: 255 seconds]
curiousguy13 has joined #mlpack
KTL has joined #mlpack
curiousguy13 has quit [Ping timeout: 244 seconds]
curiousguy13 has joined #mlpack
vedhu63w has quit [Ping timeout: 252 seconds]
KTL has quit [Ping timeout: 264 seconds]
KTL has joined #mlpack
< KTL>
naywhayare, the correct calculation of the propability depends a lot on the log determinant of the covariance matrix ... and that thing is sensitive ...
< KTL>
proposal A. since the determinant is calculated anyway derive the logdet from there, not from the covlower derived from cholesky
< KTL>
proposal B. specify the "std"-method when calling arma::det
< KTL>
proposal C. pull up the minimal required determinant way up
< KTL>
(proposal D: keep the dimensions with a 0 variance apart, only do matrix-calculations on the submatrix for the dimensions with non-zero-variances)
KTL has quit [Ping timeout: 256 seconds]
KTL has joined #mlpack
curiousguy13 has quit [Ping timeout: 256 seconds]
curiousguy13 has joined #mlpack
KTL has quit [Quit: Leaving]
decltypeme has quit [Quit: Konversation terminated!]