Abstract
For a long time neural networks have been a popular approach for intelligent machines development and knowledge discovery. Despite its tremendous success, neural network actually suffers from problems which make it unable to model human intelligence. The main issues lies in the fact that it differs significantly with the actual processes in the brain except that it is being constructed of many interconnected units following the neuron structure. This paper proposes a sequential hierarchical superset (SHS) implementation of the brain's neocortex memory system. Inspired by the recent neuroscience theory called the memory-prediction framework, the proposed approach is applied into computer network domain to perform automated network forensic analysis.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2008 International Conference on Artificial Intelligence, ICAI 2008 and Proceedings of the 2008 International Conference on Machine Learning; Models, Technologies and Applications |
Pages | 490-495 |
Number of pages | 6 |
Publication status | Published - 2008 |
Externally published | Yes |
Event | International Conference on Artificial Intelligence and International Conference on Machine Learning; Models, Technologies and Applications 2008 - Las Vegas, United States of America Duration: 14 Jul 2008 → 17 Jul 2008 |
Conference
Conference | International Conference on Artificial Intelligence and International Conference on Machine Learning; Models, Technologies and Applications 2008 |
---|---|
Abbreviated title | ICAI 2008/MLMTA 2008 |
Country/Territory | United States of America |
City | Las Vegas |
Period | 14/07/08 → 17/07/08 |
Keywords
- Brain modeling
- Knowledge representation
- Learning network behavior
- Machine intelligence method
- Neocortex memory system