Abstract
A novel mapping of the Fuzzy ART algorithm onto a neural network architecture is described. The architecture does not utilize bi-directional synapses, weight transport, or weight duplication, and requires one fewer layer of processing elements than the architecture originally proposed by Carpenter et al. (1991a). In the new architecture, execution of the algorithm takes a constant time per input vector regardless of the relationship between the input and existing templates, and several control signals are eliminated. This mapping facilitates hardware implementation of Fuzzy ART and furthermore serves as a tool for envisioning and understanding the algorithm.
Original language | English (US) |
---|---|
Pages (from-to) | 409-411 |
Number of pages | 3 |
Journal | Neural Networks |
Volume | 10 |
Issue number | 3 |
DOIs | |
State | Published - Apr 1997 |
Externally published | Yes |
Keywords
- fuzzy ART
- fuzzy ARTMAP
- neural architecture
- parallel hardware
ASJC Scopus subject areas
- Cognitive Neuroscience
- Artificial Intelligence