Context dependent pattern recognition: a framework for hybrid architectures bridging chaotic neural networks based on recursive processing elements and symbolic information

Authors:
Emilio Del-Moral-Hernandez;Humberto Sandmann;Gleison Araújo
Affiliations:
Department of Electronic Systems Engineering, Polytechnic School of the University of Sao Paulo, Brazil;Department of Electronic Systems Engineering, Polytechnic School of the University of Sao Paulo, Brazil;Department of Electronic Systems Engineering, Polytechnic School of the University of Sao Paulo, Brazil
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 9
Cited 0

Bidirectional associative memories

IEEE Transactions on Systems, Man and Cybernetics
Artificial intelligence: a modern approach

Artificial intelligence: a modern approach
Associative dynamics in a chaotic neural network

Neural Networks
Spiking Neuron Models: An Introduction

Spiking Neuron Models: An Introduction
Neural networks with chaotic recursive nodes: techniques for the design of associative memories, contrast with Hopfield architectures, and extensions for time-dependent inputs

Neural Networks - 2003 Special issue: Advances in neural networks research — IJCNN'03
2005 Special Issue: Non-homogenous neural networks with chaotic recursive nodes: Connectivity and multi-assemblies structures in recursive processing elements architectures

Neural Networks - 2005 Special issue: IJCNN 2005
Introduction to Automata Theory, Languages, and Computation (3rd Edition)

Introduction to Automata Theory, Languages, and Computation (3rd Edition)
Memory-Based Context-Sensitive Spelling Correction at Web Scale

ICMLA '07 Proceedings of the Sixth International Conference on Machine Learning and Applications
Neurodynamics of Cognition and Consciousness

Neurodynamics of Cognition and Consciousness

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work discusses a hybrid structure that conjugates connectionist associative memories and deterministic automata, for the implementation of context dependent pattern recognition. The associative component of the hybrid system is built through coupled recursive maps with bifurcation and chaotic dynamics (Recursive Processing Elements - RPEs). Its output feeds a deterministic state machine that controls the context of the pattern recognition tasks and produces related symbolic outputs. The proposal is illustrated in a scenario for context dependent (visual) pattern recognition, performed by an autonomous agent. Such "Learner" agent alternates between contexts of unsupervised image recognition and contexts of interaction with a "Teacher" agent, in supervised sections of image recognition. Computational experiments and related measures show the effectivenessof the proposal.