Abstract | ||
---|---|---|
The architecture of the human cortex is uniform and hierarchical in nature. In this paper, we build upon works on hierarchical classification systems that model the cortex to develop a neural network representation for a hierarchical spatio-temporal memory (HST-M) system. The system implements spatial and temporal processing using neural network architectures. We have tested the algorithms developed against both the MLP and the Hierarchical Temporal Memory algorithms. Our results show definite improvement over MLP and are comparable to the performance of HTM. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-642-02490-0_53 | ICONIP (1) |
Keywords | Field | DocType |
neural network representation,human cortex,hierarchical spatio-temporal memory,temporal processing,neural network model,hierarchical classification system,hierarchical temporal memory algorithm,definite improvement,neural network architecture,neural network | Nervous system network models,Hierarchical task network,Hierarchical temporal memory,Pattern recognition,Computer science,Recurrent neural network,Time delay neural network,Hierarchical network model,Artificial intelligence,Artificial neural network,Definite Improvement,Machine learning | Conference |
Volume | ISSN | ISBN |
5506 | 0302-9743 | 3-642-02489-0 |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kiruthika Ramanathan | 1 | 26 | 4.46 |
Luping Shi | 2 | 163 | 14.31 |
Jianming Li | 3 | 0 | 0.34 |
Kian Guan Lim | 4 | 60 | 5.35 |
Ming Hui Li | 5 | 0 | 0.34 |
Zhi Ping Ang | 6 | 2 | 1.08 |
Tow Chong Chong | 7 | 7 | 2.75 |