Path: utzoo!attcan!uunet!samsung!usc!wuarchive!mit-eddie!bloom-beacon!eru!hagbard!sunic!nuug!sigyn.idt.unit.no!sigyn.idt.unit.no!geirt
From: geirt@idt.unit.no (Geir Torheim)
Newsgroups: comp.ai.neural-nets
Subject: Feature maps and weight sharing
Message-ID: <1990Oct29.165830.16617@idt.unit.no>
Date: 29 Oct 90 16:58:30 GMT
Sender: news@idt.unit.no (Usenet news admin)
Reply-To: geirt@idt.unit.no (Geir Torheim)
Organization: Div. of CS & Telematics, Norwegian Institute of Technology
Lines: 26

Anybody who got any idea on how to train a back-prop net whith
layers divided into feature maps ? The units in a feature map share
weights.

I have read an article by Le Cun
about this, but he does not explain how he updates the shared weights.
I guess the best thing to do is to find the delta w for each
unit in the map and then use the average of these delta w as
the delta w for the shared weight.  If someone has other ideas,
please send me an email.

I am also interested in guidelines for
how big the receptive fields should be, and how the maps should be
interconnected. Is it a good idea to let a unit in a map connect to several 
different maps in the previous layer, like Cun do ? How much should the
receptive fields overlap ? 


I am going to use the maps in character recognition.

If there is any interest, I'll send a summary to this newsgroup.

  - Geir

-- 
  geirt@idt.unit.no       or       TORHEIM@NORUNIT  (BITNET/EARN)