[Journal papers] [Conference papers] [PhD Theses] [MSc Theses]

 

Journal paper
Convex Optimization in Training of CMAC Neural Networks
Automatika - Časopis za automatiku, mjerenje, elektroniku, računarstvo i komunikacije , Vol.42, pp.151 -- 157, 2001
ABSTRACT:
Simplicity of structure and learning algorithm plays important role in a real-time application of neural networks. The Cerebellar Model Articulation Controller (CMAC) neural network, with associative memory type of organization and Hebbian learning rule, satisfies these two conditions. But, Hebbian rule gives poor performance during on-line identification, which is used as a preparation phase for on-line implementation. In this paper we show that optimal CMAC network parameters can be found via convex optimization techniques. For standard l-2 approximation this is equivalent to the solution of Quadratic Program (QP), while for l-1 or l-inf approximation it is enough to solve Linear Program (LP). In both cases physical constraints on parameter values can be included in an easy and straightforward way.
BibTeX entry:
@article \{Baotic2001_48,
author = \{Baoti\'{c}, M. AND Petrovi\'{c}, I. AND Peri\'{c}, N.},
title = \{Convex Optimization in Training of CMAC Neural Networks},
journal = {Automatika - Časopis za automatiku, mjerenje, elektroniku, računarstvo i komunikacije },
volume = \{42},
pages = \{151 -- 157},
year = \{2001}
}
No file available for download

 

 

 

 

 

Home
About Us
People
Visitors
Groups
Projects
Publications
Software
Courses
Laboratory
Seminars
Students
Matlab
Alumni
Links