home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!saimiri.primate.wisc.edu!caen!spool.mu.edu!yale.edu!ira.uka.de!math.fu-berlin.de!informatik.tu-muenchen.de!baginski
- From: baginski@Informatik.TU-Muenchen.DE (Boris Baginski)
- Subject: Meaning of deltas in hidden units
- Keywords: BP, delta values
- Originator: baginski@gnom.informatik.tu-muenchen.de
- Sender: news@Informatik.TU-Muenchen.DE (USENET Newssystem)
- Organization: Technische Universitaet Muenchen, Germany
- Date: Tue, 15 Dec 1992 16:24:20 GMT
- Message-ID: <1992Dec15.162420.22854@Informatik.TU-Muenchen.DE>
- Lines: 15
-
-
- Everbody knows the meaning of the delta values in the backprop algorithm
- for output units (difference between target and activation) and the use
- of the deltas to adjust the internal weights.
-
- But the question is: what do those values express for the hidden units and
- for the input units (can be calculated easily, are not used) ?
- We explored that these deltas take on values up to 50 (+/-) or so, but we only
- use inputs and targets and activation states in the range of 0-1.
- So it`s not simply possible to say these values express a realistic target minus
- activation for the hidden/input units.
-
- thank you, regards,
- BORIS BAGINSKI
- adress: baginski@informatik.tu-muenchen.de
-