Menu
Content/Inhalt
About the SFB 673
Login
SFB 673
Alignment in Communication
SFB 673
Events
SFB 673
Projects
Events
Calendar
Photos
Publications
Members
Associated Members
Student Assistants
Board of directors
Colloquium
Positions available
Uni Bielefeld
DFG
Links
Workshop
Modular Network SOM and Self-Organizing Homotopy Network as a Foundation for Brain-like Intelligence
Donnerstag, 06.09.2007 09:00 - 10:00
Tetsuo Furukawa
Modular Network SOM and Self-Organizing Homotopy Network as a Foundation for Brain-like Intelligence
Abstract:
In this paper, two generalizations of the SOM are introduced. The first of these extends the SOM to deal with more generalized classes of objects besides the vector dataset. This generalization is realized by employing modular networks instead of reference vector units and is thus called a modular network SOM (mnSOM). The second generalization involves the extension of the SOM from "map" to "homotopy", allowing the SOM to deal with a set of data distributions rather than a set of data vectors. The resulting architecture is called SOMn, where each reference unit represents a tensor of rank n. These generalizations are expected to provide good platforms on which to build brain-like intelligence.
Contact
homepage:
www.techfak.uni-bielefeld.de/
Registration
Please fill in your details for registration.
First Name
Last Name
Affiliation
E-mail
Hotelroom needed
Yes
Hotelroom needed from
Hotelroom needed from
Register: