Recurrent and concurrent neural networks for objects recognition

Authors:
Federico Cecconi;Marco Campenní
Affiliations:
Laboratory of Artificial Life and Robotics, Institute of Cognitive Sciences and Technologies CNR, ROME, Italy;Laboratory of Artificial Life and Robotics, Institute of Cognitive Sciences and Technologies CNR, ROME, Italy
Venue:
AIA'06 Proceedings of the 24th IASTED international conference on Artificial intelligence and applications
Year:
2006

Citing 5
Cited 1

A cognitive architecture for artificial vision

Artificial Intelligence
Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems

Neural Networks - Special issue on organisation of computation in brain-like systems
Self-Organizing Maps

Self-Organizing Maps
Moving Object Tracking by Optimizing Active Models

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
A model for dynamic shape and its applications

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

A Testbed for Neural-Network Models Capable of Integrating Information in Time

Anticipatory Behavior in Adaptive Learning Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

A system based on a neural network framework is considered. We used two neural networks, an Elman network [1][2] and a Kohonen (concurrent) network [3], for a categorization task. The input of the system are objects derived from three general prototypes: circle, square, polygon. We varied the size and orientation of the objects in a continuous way. The system is trained using a new algorithm, based on recurrent version of backpropagation and Kohonen rule. The system achieves the capacity to predict the shape of the objects with a remarkable generalization [4]. We compare our results with the results using a classical Elman network. The model is implemented by a Matlab/Simulink environment.