Abstract
COGNET, based on a neural network first described by Fukushima, demonstrates the relationship between connectionist and other micropopulation models. Its success and physiological orientation led to an implementation using the SUMMERS simulation shell. After self-supervised learning, COGNET uses forward and backward propagation of signals to recognize partial and noisy patterns, and to reconstruct the originals. Stochastic features include variable thresholds for neuronal firing and occasional cell death. The successful implementation of COGNET demonstrates the generality of the concepts embodied in SUMMERS, which in turn promotes the reusability of software and facilitates the extension of computational models in biomedical research. COGNET itself forms a framework for building other physiologically oriented neural network models.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 215-225 |
| Number of pages | 11 |
| Journal | Computers in Biology and Medicine |
| Volume | 23 |
| Issue number | 3 |
| DOIs | |
| State | Published - May 1993 |
Bibliographical note
Funding Information:Acknowledgemen&r-Thisw ork was supportedi n part by Grant P41-RR01632fr om the NationalI nstituteso f Health. Help in preparationo f this paperw as receivedf rom numerousin dividuals.M S Jan Marie Lundgren was responsiblef or the fInal editing.D r SusanK . Seaholmi ntroducedt he schemaf or representings imulated time. Dr Jih-Jing Yang and Mr Woon-Young Yeo contributedt o somep arts of CGGNET implementation. This work formed part of the doctorald issertationin Computera nd InformationS cienceso f the first author. Retired Professor EugeneA ckermans erveda s Dr Kilis’ thesisa dviser.
Keywords
- Micropopulation model
- Neural network
- Pattern recognition
- Self-supervised learning
- Stochastic simulation