home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!munnari.oz.au!metro!basser.cs.su.oz.au!tom
- From: tom@cs.su.oz.au (Thomas James Jones)
- Subject: Re: re:need for unique test sets
- Reply-To: tom@cs.su.oz.au
- Organization: Basser Department of Computer Science
- Date: Mon, 27 Jul 1992 10:14:01 GMT
- Message-ID: <1992Jul27.101401.18276@cs.su.oz.au>
- References: <1992Jul19.070433.5896@afterlife.ncsc.mil> <25633@life.ai.mit.edu> <1992Jul22.031319.15531@afterlife.ncsc.mil>
- Sender: news@cs.su.oz.au (News)
- Lines: 32
-
- In article <1992Jul22.031319.15531@afterlife.ncsc.mil>, hcbarth@afterlife.ncsc.mil (Bart Bartholomew) writes:
-
- |>
- |> Let me try again.
- |> If you have trained the net on the training set
- |> and ithe net gets all the answers right according to some
- |> arbitrary measure (not necessarily MSE) AND if your
- |> test set contains some of the same input/output pairs as
- |> are in the training set, then the net will always get those
- |> right, and will cause the apparent success on the test set
- |> to look better than it really is. Unless, of course, it
- |> gets all the test set right, and then the point is probaly moot.
- |> The point of having a test set (taken from the same
- |> source as the training set) is to make sure the net has found
- |> the right (or equivalent) function.
- |> On the other hand, if the net does well on the training
- |> set but falls apart (scores badly) on the test set, you know that
- |> the net has found a nice function that describes the training
- |> set well, but *is not the function that actually generated the
- |> data*. In that case, the net is worthless.
-
- I guess this is pretty difficult to answer, but what
- basis do we have for expecting that the net should
- (or can) learn a function we have 'in mind', when there
- are infinite trivially different ways of mapping any
- given data set?
- If we have no organizational basis for our learning, then
- what inherent organizational concepts do we expect the
- net to extract?
-
- tom
-
-