Dynamic Memory Allocation for CMAC using Binary Search Trees
Access Status
Open access
Authors
Scarfe, Peter
Lindsay, Euan
Date
2007Type
Conference Paper
Metadata
Show full item recordCitation
Scarfe, Peter and Lindsay, Euan. 2007. : Dynamic Memory Allocation for CMAC using Binary Search Trees, in Aggarwal, Akshai and Yager, Ronald and Sandberg, I. W. (ed), 8th WSEAS International Conference on Neural Networks, 18 Jun 2007, pp. 61-66. Vancouver, Canada: WSEAS Press.
Source Title
8th WSEAS International Conference on Neural Networks
Source Conference
8th WSEAS International Conference on Neural Networks
Additional URLs
Faculty
Faculty of Engineering and Computing
Division of Engineering, Science and Computing
Department of Mechanical Engineering
Collection
Abstract
Cerebellar Model Articulation Controllers (CMACs) are a biologically-inspired neural network system suitable for trajectory control. Traditionally, CMACs have been implemented using hash-coding for their memory allocation, requiring static allocation of fixed amounts of memory in advance to the training of the system. This paper presents a method for implementing CMACs using Binary Search Trees to provide dynamic memory allocation, allowing for lower memory usage without compromising the functionality of theCMAC.
Related items
Showing items related by title, author, creator and subject.
-
De La Pierre, Marco; Orlando, R.; Ferrabone, M.; Zicovich-Wilson, C.; Dovesi, R. (2014)Symmetry can dramatically reduce the computational cost (running time and memory allocation) of Self-Consistent-Field ab initio calculations for crystalline systems. Crucial for running time is use of symmetry in the ...
-
De La Pierre, Marco; Orlando, R.; Ferrabone, M.; Zicovich-Wilson, C.; Dovesi, R. (2014)Symmetry can dramatically reduce the computational cost (running time and memory allocation) of Self-Consistent-Field ab initio calculations for crystalline systems. Crucial for running time is use of symmetry in the ...
-
Orlando, R.; De La Pierre, M; Zicovich-Wilson, C.; Erba, A.; Dovesi, R. (2014)Use of symmetry can dramatically reduce the computational cost (running time and memory allocation) of Self-Consistent-Field ab initio calculations for molecular and crystalline systems. Crucial for running time is symmetry ...