Name
Abstract | ||
|---|---|---|
CMAC Neural Network is a popular choice for control applications. One of the main problems with CMAC is that the memory needed for the network grows exponentially with each addition of input variable. In this paper, we present a new CMAC architecture with more effective allocation of the available memory space. The proposed architecture employs hierarchical clustering to perform adaptive quantization of the input space by capturing the degree of variation in the output target function to be learned. We showed through a car maneuvering control application that using this new architecture, the memory requirement can be reduced significantly compared with conventional CMAC while maintaining the desired performance quality. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1007/11550907_74 | ICANN (2) |
Keywords | Field | DocType |
control application,cmac neural network,available memory space,input space,conventional cmac,car maneuvering control application,new architecture,memory requirement,hierarchical clustering,new cmac architecture,efficient memory allocation,proposed architecture,memory allocation,neural network | Hierarchical clustering,Adaptive method,Computer science,Memory management,Artificial intelligence,Formal methods,Artificial neural network,Quantization (signal processing),Machine learning,Memory architecture,Memory cell | Conference |
Volume | ISSN | ISBN |
3697 | 0302-9743 | 3-540-28755-8 |
Citations | PageRank | References |
0 | 0.34 | 7 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sintiani Dewi Teddy | 1 | 36 | 3.50 |
| Edmund M. -K. Lai | 2 | 55 | 5.44 |