Abstract | ||
---|---|---|
This paper presents an extension of active neural associative knowledge graphs (ANAKG) to their mini-column form where each symbol is represented several times. We demonstrate that this new associative memory organization preserves all properties of ANAKG memories like storage of knowledge based on spatio-temporal input sequences, while increasing recall quality, memory capacity, and its resolution for short-term memory recall. The implemented model combines ANAKG associative neuron idea with the idea of a hierarchical temporal memory that uses a mini-column form of symbol representation. Performed tests confirm our claims of higher resolution and higher memory capacity of the new associative knowledge graph. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/SSCI.2017.8285413 | 2017 IEEE Symposium Series on Computational Intelligence (SSCI) |
Keywords | Field | DocType |
associative semantic memory,associative neurons,associative connections,mini-column structure,knowledge representation | Knowledge representation and reasoning,Knowledge graph,Associative property,Content-addressable memory,Hierarchical temporal memory,Symbol,Computer science,Theoretical computer science,Recall | Conference |
ISBN | Citations | PageRank |
978-1-5386-2727-3 | 0 | 0.34 |
References | Authors | |
8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Basawaraj | 1 | 15 | 2.09 |
Janusz A. Starzyk | 2 | 440 | 36.95 |
Adrian Horzyk | 3 | 53 | 12.76 |