ADAPTIVE RESONANCE THEORY

Views:
 
Category: Education
     
 

Presentation Description

No description available.

Comments

Presentation Transcript

PowerPoint Presentation: 

PRESENTED BY:- SONIA SIWATCH PRESENTED BY:- SONIA SIWATCH ROLL NO 102609

PowerPoint Presentation: 

Learning = learning by adaptation The young animal learns that the green fruits are sour, while the yellowish/reddish ones are sweet. The learning happens by adapting the fruit picking behaviour. At the neural level the learning happens by changing of the synaptic strengths, eliminating some synapses, and building new ones. 10/6/2012 2 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 3 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 4 ADAPTIVE RESONANCE THEORY It is based on a labeled training set. The class of each piece of data in training set is known. Class labels are pre-determined and provided in the training phase .

PowerPoint Presentation: 

10/6/2012 5 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 6 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 7 ADAPTIVE RESONANCE THEORY Learning useful structure without labeled classes, optimization criterion, feedback signal, or any other information beyond the raw data

PowerPoint Presentation: 

Adaptive Resonance Theory (ART) is a theory developed by Stephen Grossberg and Gail Carpenter on aspects of how the brain processes information. It describes a number of neural network models which use supervised and unsupervised learning methods, and address problems such as pattern recognition and prediction. The adaptive resonance theory (ART) has been developed to avoid the stability-plasticity dilemma (SPD) in competitive networks learning. 10/6/2012 8 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 9 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

Basic ART structure consist of Comparison field and recognition field composed of neuron Vigilance parameter Reset module COMPARISON FIELD:- It takes an input vector and transfer it to its best match in recognition field. RECOGNITION FIELD:- The cluster units , also called a competitive layer. 10/6/2012 10 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

VIGILANCE PARAMETER:- After input vector is classified , a reset module compares the strength of the recognition match to a vigilance parameter. RESET MODULE:- To control the degree of similarity of pattern placed on the same cluster. 10/6/2012 11 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

TRAINING:- There are two basic methods of training ART-based neural networks:- SLOW AND FAST. In the SLOW LEARNING METHOD , the degree of training of the recognition neuron’s weights towards the input vector is calculated to continuous values with differential equations and is thus dependent on the length of time the input vector is presented. WITH FAST LEARNING , algebraic equations are used to calculate degree of weight adjustments to be made, and binary values are used. 10/6/2012 12 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 13 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 14 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

ART1 is the simplest ART learning model specifically designed for recognizing binary patterns. The ATTENTIONAL SUBSYSTEM consists of two competitive networks, the comparison layer F1 and the recognition layer F2, and two control gains, Gain 1 and Gain 2. The ORIENTING SUBSYSTEM contains the reset layer for controlling the attentional subsystem overall dynamics. The COMPARISON LAYER receives the binary external input passing it to the recognition layer responsible for matching it to a classification category. This result is passed back to the comparison layer to find out if the category matches that of the input vector. If there is a match a new input vector is read and the cycle starts again. If there is a mismatch the orienting system is in charge of inhibiting the previous category in order to get a new category match in the RECOGNITION LAYER. The two gains control the activity of the recognition and comparison layer, respectively. 10/6/2012 15 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 16 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

ART 2:- ART-2 an extension of ART-1, used to cluster analog data. Fuzzy ART:- It implements fuzzy logic into ART’s pattern recognition. ARTMAP:- A supervised learning mechanism for binary data. Fuzzy ARTMAP :- A supervised learning algorithm for analog data. 10/6/2012 17 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 18 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 19 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 20 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

10/6/2012 21 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

Solves Stability – Plasticity Dilemma. Forms new memories or incorporates new information based on a predefined vigilance parameter. It describes a number of neural network models which use supervised and unsupervised learning methods, and address problems such as pattern recognition and prediction. 10/6/2012 22 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

Santosh K. Rangarajan , Vir V. Phoha , Kiran S. Balagani , Rastko R.Selmic , S.S. Iyengar , "Adaptive Neural Network Clustering of Web Users," Computer , Vol. 37, No. 4, pp. 34-40, Apr, 2004. Gail A. Carpenter, and Stephen Grossberg , “Adaptive Resonance Theory”, The Handbook of Brain Theory and Neural Networks , Ed. 2, Sep, 1998. Gail A. Carpenter, “Default ARTMAP”, Neural Networks , July, 2003. Tao Jiang, Ah- Hwee Tan, “Learning Image-Text Associations”, (Not yet published), 2008. Jianhong Luo , and Dezhao Chen, “An Enhanced ART2 Neural Network for Clustering Analysis”, Proceedings of the 1st international conference on Forensic applications and techniques in telecommunications, information, and multimedia and workshop , 2008. 10/6/2012 23 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

6. E.P. Sapozhnikova , V.P. Lunin , "A Modified Search Procedure for the Art Neural Networks," ijcnn,pp.5541, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00) -Volume 5, 2000. 7. Gail A. Carpenter, and Stephen Grossberg , “The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network”, Computer , Vol. 21, No. 3, pp. 77-88, Mar., 1988. 8. Robert A. Baxter, “Supervised Adaptive Resonance Networks”, Proceedings of the conference on Analysis of neural network applications, pp. 123 – 137, 1991. 9. Pui Y. Lee, Siu C. Hui ., and Alvis Cheuk Fong, “Neural Networks for Web Content Filtering”, IEEE Intelligent Systems , Vol. 17, No. 5, pp. 48-57, Sept., 2002. 10.“Adaptive Resonance Theory”, Wikipedia , http://en.wikipedia.org/wiki/Adaptive_resonance_theory. 10/6/2012 24 ADAPTIVE RESONANCE THEORY

PowerPoint Presentation: 

25