RE: Have you ?

Brennand, Giles (Giles_Brennand@atkearney.com)
Fri, 15 Jan 1999 20:02:42 +0100 (MET)

I'm not sure there are any 'standards'! My perspective is that there are
three levels to test
1) Does the code implement the algorithm?
2) Does the algorithm perform as expected?
3) Does the algorithm usefully model the real world?

The first level of testing corresponds to unit testing in conventional SDLC;
the second to integration or system testing; and the third to user
acceptance testing. For a system of any complexity, level 2 cannot
typically be addressed through expected results of test cases, but rather
needs a Monte Carlo perspective to test the likelihood of the distribution
of outputs. Otherwise, the challenges in Level 1 and Level 3 correspond
fairly closely to those of conventional systems development.
> -----Original Message-----
> From: Agnes [SMTP:lowht@pl.jaring.my]
> Sent: 11 January 1999 11:50
> To: Multiple recipients of list
> Subject: Have you ?
>
> Hi there...
>
> Have you tried implementing any application using some AI approach (e.g.
> Fuzzy Logic, Genetic Algorithm, Neural Networks, Finite State Machine
> etc.) ?
>
> If yes, may I know what types of testing that you have carried out to
> determine the accuracy and correctness of the application ?
>
> This is the first time I try to use GA in my application ( I used to be
> involved in conventional system development and they have some testing
> strategies like unit test, module test, integration test and so on ).
> It's almost come to the end which I intend to carry out some testing to
> it.... Therefore I'm wonder is there some standard / common types of
> procedures involve in testing AI types of application.... Please let me
> know if there is....
>
> Thanks in advance.
>
> Regards,
> Agnes
>
>
>
> ##########################################################################
> ##
> This message was posted through the fuzzy mailing list.
> (1) To subscribe to this mailing list, send a message body of
> "SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at
> (2) To unsubscribe from this mailing list, send a message body of
> "UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL
> yoursubscription@email.address.com"
> to listproc@dbai.tuwien.ac.at
> (3) To reach the human who maintains the list, send mail to
> fuzzy-owner@dbai.tuwien.ac.at
> (4) WWW access and other information on Fuzzy Sets and Logic see
> http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info
> (5) WWW archive:
> http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html

############################################################################
This message was posted through the fuzzy mailing list.
(1) To subscribe to this mailing list, send a message body of
"SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at
(2) To unsubscribe from this mailing list, send a message body of
"UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com"
to listproc@dbai.tuwien.ac.at
(3) To reach the human who maintains the list, send mail to
fuzzy-owner@dbai.tuwien.ac.at
(4) WWW access and other information on Fuzzy Sets and Logic see
http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info
(5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html