Recurrent and concurrent neural networks for objects recognition
Pages 216 - 221
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.
References
[1]
{1} J. Elman. Finding structure in time. Cognitive Science , 14:179-211, 1990.
[2]
{2} Federico Cecconi and Domenico Parisi. Networks that learn to predict where the food is and also to eat it. Proc. IJCNN International Joint Conference on Neural Networks, Washington, USA, 1989.
[3]
{3} T. Kohonen. Self-Organizing Maps. (Springer, Berlin, 1995).
[4]
{4} L.A. Machowski and T. Marwala. Representing and classifying 2d shapes of real-world objects using neural networks. Proc. IEEE International Conf. on Systems, Man and Cybernetics, The Hague, The Netherlands, 2004, 7:6366-6372.
[5]
{5} B. Sun and F. Takeda. Research on the neural network with rbf for currency recognition. Proc. IASTED International Conf. on Neural Networks and Computational Intelligence, Grindelwald, Switzerland, 2004, 201-205.
[6]
{6} C.-B. Liu and N. Ahuja. A model for dynamic shape and its applications. Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition , Washington, USA, 2004, 2:129-134.
[7]
{7} Pramath R. Sinha and Ruzena K. Bajcsy. Robotic exploration of surfaces and its application to legged locomotion. Proc. IEEE International Conf. on Robotics and Automation, Nice, France, 1992, 221-226.
[8]
{8} Jeffrey A. Fayman, Ehud Rivlin, and Henrik I. Christensen. System for active vision driven robotics. Proc. IEEE, International Conf. on Robotics and Automation , Minneapolis, Minnesota, USA, 1996, 3:1986-1992.
[9]
{9} N.J.T. Thomas. Are theories of imagery theories of imagination? an active perception approach to conscious mental content. Cognitive Science, 23(2):207-245, 1999.
[10]
{10} Daesik Jang and Hyung-Il Choi. Moving object tracking using active models. Proc. IEEE International Conf. on Image Processing, Genova, Italy, 1998, 3:648-652.
[11]
{11} R. Eckhorn, H. J. Reitboeck, M. Arndt, and P. W. Dicke. Feature linking via synchronization among distributed assemblies: Simulation of results from cat cortex. Neural Computation, 2:293-307, 1990.
[12]
{12} M. Shanahan. Perception as abduction: Turning sensor data into meaningful representation. Cognitive Science, 29(1):103-134, 2005.
[13]
{13} J. Tani and S. Nolfi. Learning to perceive the world as articulated: An approach for hierarchical learning in sensory-motor systems. Neural Networks, 12:1131-1141, 1999.
[14]
{14} G. Cannata and E. Grosso. Active eye-head control. Proc. IEEE International Conf. on Robotics and Automation , San Diego, USA, 1994, 4:2837-2843.
[15]
{15} A. Chella, M. Frixione, and S. Gaglio. A cognitive architecture for artificial vision. Artificial Intelligence, 89:73-111, 1997.
[16]
{16} T. Ziemke, D.A. Jirenhed, and G. Hesslow. Internal simulation of perception: a minimal neurorobotic model. 2005.
[17]
{17} KTeam S.A. Khepera user manual. (http://www.k-team.com/download/khepera.html, 2005).
Index Terms
- Recurrent and concurrent neural networks for objects recognition
Recommendations
Training Many-to-Many Recurrent Neural Networks with Target Propagation
Artificial Neural Networks and Machine Learning – ICANN 2021AbstractDeep neural networks trained with back-propagation have been the driving force for the progress in fields such as computer vision, natural language processing. However, back-propagation has often been criticized for its biological implausibility. ...
Prediction of air pollution using LSTM-based recurrent neural networks
This paper proposes a system that predicts the pollution level at some hour at a place. It also infers about the various parameters associated with the increasing pollution across the globe, its ill effects and the future scenario of the same. An air ...
New Results for Prediction of Chaotic Systems Using Deep Recurrent Neural Networks
AbstractPrediction of nonlinear and dynamic systems is a challenging task, however with the aid of machine learning techniques, particularly neural networks, is now possible to accomplish this objective. Most common neural networks used are the multilayer ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Publisher
ACTA Press
United States
Publication History
Published: 13 February 2006
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 23Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 13 Nov 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in