liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Associative Memories with Short--Range Higher Order Couplings
Linköping University, Department of Electrical Engineering, Computer Vision . Linköping University, The Institute of Technology.
1993 (English)In: Neural Networks, ISSN 0893-6080, Vol. 6, no 3, 409-421 p.Article in journal (Refereed) Published
Abstract [en]

A study of recurrent associative memories with exclusively short-range connections is presented. To increase the capacity, higher order couplings are used. We study capacity and pattern completion ability of networks consisting of units with binary (±1) output. Results show that perfect learning of random patterns is difficult for very short coupling ranges, and that the average expected capacities (allowing small errors) in these cases are much smaller than the theoretical maximum, 2 bits per coupling. However, it is also shown that by choosing ranges longer than certain limit sizes, depending on network size and order, we can come close to the theoretical capacity limit. We indicate that these limit sizes increase very slowly with net size. Thus, couplings to at least 28 and 36 neighbors suffice for second order networks with 400 and 90,000 units, respectively. From simulations it is found that even networks with coupling ranges below the limit size are able to complete input patterns with more than 10% errors. Especially remarkable is the ability to correct inputs with large local errors (part of the pattern is masked). We present a local learning algorithm for heteroassociation in recurrent networks without hidden units. The algorithm is used in a multinet system to improve pattern completion ability on correlated patterns.

Place, publisher, year, edition, pages
1993. Vol. 6, no 3, 409-421 p.
Keyword [en]
Short-range couplings; Higher order neurons; Many-neuron interactions; Associative memory; Recurrent networks; Pattern completion; Error correction; Physics of neural networks
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-21593DOI: 10.1016/0893-6080(93)90008-KOAI: diva2:241555
Available from: 2009-10-04 Created: 2009-10-04 Last updated: 2009-10-04

Open Access in DiVA

No full text

Other links

Publisher's full text
By organisation
Computer Vision The Institute of Technology
In the same journal
Neural Networks
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 114 hits
ReferencesLink to record
Permanent link

Direct link