Adaptive Resonance Theory

Adaptive Resonance Theory

1. Adaptive Resonance Theory Presented By: D Surat M.Sc. Physics ( Elec.) Dayalbagh educational Institute

2. Outline Adaptive Resonance Theory basics ART Classification ART Networks Basic ART Network Architecture ART Algorithm

3. ART:Basics ART stands for Adaptive resonance 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. Address problems such as pattern recognition and prediction.

4. ART:Basics(Cont’d ) The term “resonance” refers to a resonant state of a neural network in which a category prototype vector matches close enough to the current input vector. ART matching leads to this resonant state, which permits learning. The network learns only in its resonant state.

5. ART Classification

6. • ART 1 : ▫ simplest variety of ART networks ▫ accepting only binary inputs. • ART2 : ▫ support continuous inputs. • ART3 is refinement of both models. • Fuzzy ART implements fuzzy logic into ART’s pattern recognition. • ARTMAP also known as Predictive ART, combines two slightly modified ART-1 or ART-2 units into a supervised learning structure . • Fuzzy ARTMAP is merely ARTMAP using fuzzy ART units, resulting in a corresponding increase in efficacy.

7. ART Networks The basic ART system is unsupervised learning model . It typically consists of 1 . a comparison field 2 . a recognition field composed of neurons, 3 . a vigilance parameter, and 4 . a reset module

8. Comparison field: The comparison field takes an input vector and transfer it to its best match in the recognition field. Its best match is the single neuron whose set of weights most closely matches the input vector. Recognition field: Each recognition field neuron, outputs a negative signal proportional to that neuron’s quality of match to the input vector to each of the other recognition field neurons and inhibits their output accordingly

9. Vigilance parameter: After the input vector is classified, a reset module compares the strength of the match to a vigilance parameter. The vigilance parameter has cansidrable influence on the system: - Higher vigilance produces highly detailed memories. - lower vigilance results in more general memories . Reset module: The reset module compares the strengh of the recognition match to the vigilance parameter. - if the vigilance threshold is met, then training commences. - otherwise, if the match level does not meet the vigilance parameter, then the firing recognition neuron is inhibited until a new input vector is applied.

10. Basic ART Network Architecture

11. ART Algorithm Input is presented (in layer 1). • Forward transmission via bottom-up weights(Inner product) • Best matching node fires (winner-take-all layer) Comparison Phase (in Layer 1) • Backward transmission via top-down weights • Vigilance test: class template matched with input pattern. If pattern close enough to template, categorisation was successful and “resonance” achieved

12. • If not close enough reset winner neuron and try next best matching • (The reset inhibit the current winning neuron, and the current expectation is removed) • A new competition is then performed in Layer 2, while the previous winning neuron is disable. • The new winning neuron in Layer 2 projects a new expectation to Layer 1, through the L2-L1 connections . • This process continues until the L2-L1 expectation provides a close enough match to the input pattern. • The process of matching, and subsequent adaptation, is referred to as resonance

13. Summary

14. Example cluster of the vectors 11100,11000,00001,00011 low vigilance: 0.3 High vigilance: 0.7

15. W ith ρ =0.3

16. W ith ρ =0.7

17. Applications • Face recognition • Image compression • Mobile robot control • Target recognition • Medical diagnosis • Signature verification

18. Reference https:// en.wikipedia.org/wiki/Adaptive_resonance_theory http:// www.myreaders.info/05-Adaptive_Resonance_Theory.pdf http://vp.dei.ac.in:8081/data/NN/presentations/PHM802_NN_LP11.pdf

19. Thank You !!