Demon-Based associative memories
Cybernetics and Systems
Self-organization and associative memory: 3rd edition
Self-organization and associative memory: 3rd edition
Associative neural memories
| Hi-index | 0.00 |
Resurrecting an old model of associative memory, the authors find a way to give it surprising new life. DEHAM memories, (DEmon HeteroAssociative Memory), depend on communities of cell like processing entities that become specialists on what the output should be when they see certain numeric features at the input side of the memory. A voting-like process is used to correct weak information. Here we investigate a way to extend DEHAM memories to real numbers (not just binary data) and we observe that their inherent ease of implementation makes them fit nicely into an undergraduate artificial intelligence course.