home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!munnari.oz.au!metro!usage!spectrum!s8818037
- From: s8818037@spectrum.cs.unsw.oz.au (Matthew James Leayr)
- Subject: function approximation with nets.
- Message-ID: <1992Sep14.053408.20681@usage.csd.unsw.OZ.AU>
- Sender: news@usage.csd.unsw.OZ.AU
- Nntp-Posting-Host: 149.171.240.26
- Organisation: University Of New South Wales
- Reply-To: s8818037@spectrum.cs.unsw.oz.au (Matthew James Leayr)
- Organization: none
- Date: Mon, 14 Sep 1992 05:34:08 GMT
- Lines: 17
-
-
-
- Hi,
- I was wondering how one would go about training a network to perform
- an operation such as conversion from x-y to polar coordinates. Do you simply
- present examples of the conversion to the net in the training data? If so,
- how well suited are neural networks to this sort of task? Could a NN be used
- to perform a log-polar coordinate transform?
- Also, does anyone have any information regarding size and rotational
- invariance in neural networks?
-
-
- Thanks.
- Matt.
-
- s8818037@spectrum.cs.unsw.oz.au
-
-