New challenges in US Navy tactical vehicle applications require flexible adaptive structures for real-time intelligent system identification and control tasks. Due to its speed of computation and linear learning behavior, the architecture of lattice-based associative memory networks is particularly attractive. The main problem of these networks is the curse of dimensionality, which means that the memory requirement is exponentially dependent on the input dimension. In this paper, a novel structure called multi-resolution associative memory (MAM) network is proposed to overcome the curse of dimensionality. Preliminary simulations and real-time experiments are performed using this structure, and the results are discussed. A fuzzy rule-bare system is also proposed as a method to implement the heuristic that is at the heart of the MAM network's training algorithm.
Intelligent training of a multi-resolution associative memory network
1998
6 Seiten, 11 Quellen
Conference paper
English
Associative Memory Network Construction Algorithms
British Library Conference Proceedings | 1994
|Experimental Optoelectronic Associative Memory
NTRS | 1992
|Efficient serial associative memory
IEEE | 1993
|Dynamical quality in bidirectional associative memory neural network model
British Library Online Contents | 2013
|A compact optical associative memory
Tema Archive | 1991
|