High-order associative memories for pattern recognition

Authors:
Iulian B. Ciocoiu
Affiliations:
Faculty of Electronics and Telecommunications, Technical University of Iasi, Iasi, Romania
Venue:
ICS'08 Proceedings of the 12th WSEAS international conference on Systems
Year:
2008

Citing 8
Cited 0

Original Contribution: Associative memory with nonmonotone dynamics

Neural Networks
A normal form projection algorithm for associative memory

Associative neural memories
Face Recognition: Features Versus Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Discriminant Waveletfaces and Nearest Feature Classifiers for Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
RBF-based neurodynamic nearest neighbor classification in real pattern space

Pattern Recognition
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Analog decoding using a gradient-type neural network

IEEE Transactions on Neural Networks
Face recognition: a convolutional neural-network approach

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gradient dynamic systems with RBF-type Lyapunov functions acting as associative memories are used in several pattern recognition applications. The system exhibits stable equilibrium points in predefined positions given by the feature vectors computed from the training sets. Experimental results for face recognition and OCR tasks are reported, indicating improved performances over standard PCA and LDA-based approaches.