Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 Combining Multiple Modes of Information using Unsupervised Neural Classifiers Neural Computing Group, Department.

Similar presentations


Presentation on theme: "1 Combining Multiple Modes of Information using Unsupervised Neural Classifiers Neural Computing Group, Department."— Presentation transcript:

1 1 Combining Multiple Modes of Information using Unsupervised Neural Classifiers http://www.computing.surrey.ac.uk/ncg/ Neural Computing Group, Department of Computing, School of Electronics and Physical Sciences, University of Surrey Khurshid Ahmad, Bogdan Vrusias, Matthew Casey, Panagiotis Saragiotis

2 2 Content Report on preliminary experiments to: –Attempt to improve classification through combining modalities of information –Use a modular co-operative neural network system combining unsupervised learning techniques Tested using: –Scene-of-crime images and collateral text –Number magnitude and articulation

3 3 Background Consider how we may improve classification through combination: –Combining like classifiers (e.g. ensemble systems) –Combining expert classifiers (e.g. modular systems) Concentrate on a modular approach to combining modalities of information –For example, Kittler et al (1998): Personal identity verification using frontal face, face profile and voice inputs

4 4 Multi-net Systems Concept of combining neural network systems has been discussed for a number of years –Both ensemble and modular systems –Ensemble more prevalent Term multi-net systems has been promoted by Sharkey (1999, 2002) who recently advocated the use of modular systems –For example, mixture-of-experts by Jacobs et al 1991

5 5 Multi-net Systems Neural network techniques for classification tend to subscribe to the supervised learning paradigm –Ensemble methods –Mixture-of-experts Exceptions include Lawrence et al (1997) and Ahmad et al (2002) Unsupervised techniques give rise to problems of interpretation

6 6 Self-organised Combinations Our approach is based upon the combination of different Hebbian-like learning systems Hebb’s neurophysiological postulate (1949) –Strength of connection is increased when both sides of the connection are active

7 7 Self-organised Combinations Willshaw & von der Malsburg (1976) –Used Hebbian learning to associate patterns of activity in a 2-d pre-synaptic (input) layer and a 2-d post- synaptic (output) layer –Pre-synaptic neurons become associated with post- synaptic neurons Kohonen (1997) extended this in his Self- organising Map (SOM) –Statistical approximation of the input space –Topological map showing relatedness of input patterns –Clusters used to show classes

8 8 Self-organised Combinations Our architecture builds further on this using the multi-net paradigm Can be compared to Hebb’s superordinate combination of cell assemblies Two SOMs linked by Hebbian connections –One SOM learns to classify a primary modality of information –One SOM learns to classify a collateral modality of information –Hebbian connections associate patterns of activity in each SOM

9 9 Self-organised Combinations SOMs and Hebbian connections trained synchronously...... Primary SOM Bi-directional Hebbian Network Primary Vector Collateral Vector Collateral SOM

10 10 Self-organised Combinations Hebbian connections associate neighbourhoods of activity –Not just a one-to-one linear association –Each SOM’s output is formed by a pattern of activity centred on the winning neuron for the primary and collateral input Training complete when both SOM classifiers have learned to classify their respective inputs

11 11 Classifying Images and Text BodyFull length shot of body Single objects (close-up) Nine millimetre browning high power self-loading pistol ClassPrimary ImageCollateral Text

12 12 Classifying Images and Text Classify images based upon images and texts Primary modality of information: –66 images from the scene-of-crime domain –112-d vector based upon colour, edges and texture Collateral modality of information: –66 texts describing image content –50-d binary vector term frequency analysis 8 expert defined classes 58 vector pairs used for training, 8 for testing

13 13 Training Image SOM: 15 by 15 neurons Text SOM: 15 by 15 neurons Initial random weights Gaussian neighbourhood function with initial radius 8 neurons, reducing to 1 neuron Exponentially decreasing learning rate, initially 0.9, reducing to 0.1 Hebbian connection weights normalised Trained for 1000 epochs

14 14 Testing Tested with 8 image and text vectors –Successful classification if test vector’s winner corresponds with identified cluster for class Image SOM: –Correctly classified 4 images Text SOM: –Correctly classified 5 texts

15 15 Testing For misclassified images –Text classification was determined –Translated into image classification via Hebbian activation Similarly for misclassified texts Image SOM: –Further 3 images classified out of 4 (total 7 out of 8) Text SOM: –Further 2 texts classified out of 3 (total 7 out of 8)

16 16 Comparison Contrast with single modality of classification in image or text SOM Compared with a single SOM classifier –15 by 15 neurons –Trained on combined image and text vectors (162-d vectors) –3 out of 8 test vectors correctly classified

17 17 Classifying Number Classify numbers based upon (normalised) image or articulation? Primary modality of information: –Magnitude representation of the numbers 1 to 22 –66-d binary vector with 3 bits per magnitude Collateral modality of information: –Articulation representation of the numbers 1 to 22 –16-d vector representing phonemes 22 different numbers to classify 16 vector pairs used for training, 6 testing

18 18 Training Magnitude SOM: 66 by 1 neurons Articulation SOM: 16 by 16 neurons Initial random weights Gaussian neighbourhood function with initial radius 33 (primary) and 8 (collateral) neurons, reducing to 1 neuron Exponentially decreasing learning rate, initially 0.5 Hebbian connection weights normalised Trained for 1000 epochs

19 19 Testing Tested with 6 magnitude and articulation vectors –Successful classification if test vector’s winner corresponds with identified cluster for class Magnitude SOM: –Correctly classified 6 magnitudes –Magnitudes arranged in a ‘number line’ Articulation SOM: –Similar phonetic responses, but essentially misclassified all 6 articulations

20 20 Testing For misclassified articulation vectors –Magnitude classification was determined –Translated into articulation classification via Hebbian activation Articulation SOM: –3 articulation vectors classified out of 6 –Remaining 3 demonstrate that Hebbian association not sufficient to give rise to better classification

21 21 Comparison Contrast with single modality of classification in magnitude or articulation SOM Compared with a single SOM classifier –16 by 16 neurons –Trained on combined magnitude and articulation vectors (82-d vectors) –Misclassified all 6 articulation vectors –SOM shows test numbers are similar in ‘sound’ to numbers in the training set –Combined SOM does not demonstrate ‘number line’ and cannot capitalise upon it

22 22 Summary Preliminary results show that: –Modular co-operative multi-net system using unsupervised learning techniques can improve classification with multiple modalities –Hebb’s superordinate combination of cell assemblies? Future work: –Evaluate against larger sets of data –Further understanding of clustering and classification in SOMs –Further explore linkage of neighbourhoods, more than just a one-to-one mapping, and theory underlying model

23 23 Acknowledgements Supported by the EPSRC Scene of Crime Information System project (Grant No.GR/M89041) –University of Sheffield –University of Surrey –Five UK police forces Images supplied by the UK Police Training College at Hendon, with text transcribed by Chris Handy

24 24 References Ahmad, K., Casey, M.C. & Bale, T. (2002). Connectionist Simulation of Quantification Skills. Connection Science, vol. 14(3), pp. 165-201. Jacobs, R.A., Jordan, M.I. & Barto, A.G. (1991). Task Decomposition through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks. Cognitive Science, vol. 15, pp. 219-250. Hebb, D.O. (1949). The Organization of Behavior: A Neuropsychological Theory. New York: John Wiley & Sons. Kittler, J., Hatef, M., Duin, R.P.W. & Matas, J. (1998). On Combining Classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20(3), pp. 226-239. Kohonen, T. (1997). Self-Organizing Maps, 2nd Ed. Berlin, Heidelberg, New York: Springer- Verlag. Lawrence, S., Giles, C.L., Ah Chung Tsoi & Back, A.D. (1997). Face Recognition: A Convolutional Neural Network Approach. IEEE Transactions on Neural Networks, vol. 8(1), pp. 98-113. Sharkey, A.J.C. (1999). Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems. Berlin, Heidelberg, New York: Springer-Verlag. Sharkey, A.J.C. (2002). Types of Multinet System. In Roli, F. & Kittler, J. (Ed), Proceedings of the Third International Workshop on Multiple Classifier Systems (MCS 2002), pp. 108-117. Berlin, Heidelberg, New York: Springer-Verlag. Willshaw, D.J. & von der Malsburg, C. (1976). How Patterned Neural Connections can be set up by Self-Organization. Proceedings of the Royal Society, Series B, vol. 194, pp. 431-445.

25 25 Combining Multiple Modes of Information using Unsupervised Neural Classifiers http://www.computing.surrey.ac.uk/ncg/ Neural Computing Group, Department of Computing, School of Electronics and Physical Sciences, University of Surrey Khurshid Ahmad, Bogdan Vrusias, Matthew Casey, Panagiotis Saragiotis

26 26 Multi-net Systems Sharkey (2002) – Types of Multi-net System


Download ppt "1 Combining Multiple Modes of Information using Unsupervised Neural Classifiers Neural Computing Group, Department."

Similar presentations


Ads by Google