2. INTRODUCTION TO NEURAL NETWORKS

3. 2 A new sort of computer What are (everyday) computer systems good at... and not so good at? Good at..Not so good at.. Rule-based systems: doing what the programmer wants them to do Dealing with noisy data Dealing with unknown environment data Massive parallelism Fault tolerance Adapting to circumstances

4. 3 Neural networks to the rescue… Neural network: information processing paradigm inspired by biological nervous systems, such as our brain Structure: large number of highly interconnected processing elements (neurons) working together Like people, they learn from experience (by example)

5. 4 What is NN? “Data processing system consisting of a large number of simple, highly interconnected processing elements (artificial neurons) in an architecture inspired by the structure of the cerebral cortex of the brain” (Tsoukalas & Uhrig, 1997).

6. 5 Inspiration from Neurobiology Human Biological Neuron

7. 6 Inspiration from Neurobiology A neuron: many-inputs / one-output unit output can be excited or not excited incoming signals from other neurons determine if the neuron shall excite ("fire") Output subject to attenuation in the synapses, which are junction parts of the neuron Signal Processing

8. 7 Four basic components of a human biological neuron The components of a basic artificial neuron Inspiration from Neurobiology Artificial Neuron

9. 8 Neural networks are configured for a specific application, such as pattern recognition or data classification, through a learning process In a biological system, learning involves adjustments to the synaptic connections between neurons  same for artificial neural networks (ANNs) Inspiration from Neurobiology

10. 9 NN deals with training samples belonging to known classes and finding a generalized classifier to predict the class for any new samples. Hidden layer Output layer Input layer Attribute 1 NN general architecture Attribute 2 Attribute 3 NN General Architecture Inspiration from Neurobiology

11. 10 Where can neural network systems help… when we can't formulate an algorithmic solution. when we can get lots of examples of the behavior we require. ‘learning from experience’ when we need to pick out the structure from existing data.

12. 11 History 1943 McCulloch-Pitts neurons 1949 Hebb’s law 1958 Perceptron (Rosenblatt) 1960 Adaline, better learning rule (Widrow, Huff) 1969 Limitations (Minsky, Papert) 1972 Kohonen nets, associative memory

13. 12 1977 Brain State in a Box (Anderson) 1982 Hopfield net, constraint satisfaction 1985 ART (Carpenter, Grossfield) 1986 Backpropagation (Rumelhart, Hinton, McClelland) 1988 Neocognitron, character recognition (Fukushima) History

14. 13 Characterizations Architecture – a pattern of connections between neurons Learning Algorithm – a method of determining the connection weights Activation Function

15. 14 Problem Domains Storing and recalling patterns Classifying patterns Mapping inputs onto outputs Grouping similar patterns Finding solutions to constrained optimization problems

16. 15. Input layer Output layer Input patterns 00 11 11 01 11 00 10 01 11 11 11 Sorted patterns 00 10 STOP Coronary Disease Neural Net Problem Domains

17. 16 01 11 00 10 1111 00 10 Problem Domains

18. 17 Features Neurons can generalize novel input stimuli Neurons are fault tolerant and can sustain damage

19. 18 Who is interested?... Electrical Engineers – signal processing, control theory Computer Engineers – robotics Computer Scientists – artificial intelligence, pattern recognition Mathematicians – modelling tool when explicit relationships are unknown

20. 19 ANN Applications Signal processing Pattern recognition, e.g. handwritten characters or face identification. Diagnosis or mapping symptoms to a medical case. Speech recognition Human Emotion Detection Educational Loan Forecasting

21. 20 Male Age Temp WBC Pain Intensity Pain Duration 37101120 1 adjustable weights 0 1 00000 Appendicitis Diverticulitis Perforated Non-specific Cholecystitis Small Bowel Pancreatitis Obstruction Pain Duodenal Ulcer 37101120 1 Abdominal Pain Prediction ANN Applications

22. 21 Voice Recognition ANN Applications

23. 22 Educational Loan Forecasting System ANN Applications