1 / 24

Neural Network

Neural Network. Developed by: Dr Eddie Ip Modified by: Dr Arif Ansari. Outline. Where in business is NN used? How does it work? A function approximation method Case study. NN: Overview. Wall Street’s “rocket science” Long history: 1950 Compete with expert system

rmaldonado
Download Presentation

Neural Network

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Neural Network Developed by: Dr Eddie Ip Modified by: Dr Arif Ansari

  2. Outline • Where in business is NN used? • How does it work? • A function approximation method • Case study

  3. NN: Overview • Wall Street’s “rocket science” • Long history: 1950 • Compete with expert system • Several generations of ANN • Lab research • Hype : thinking machine • Practical apps in fast chips

  4. NN: Overview • A handwritten recognition example • http://members.aol.com/Trane64/java/JRec.html

  5. NN: Overview • Learn by examples : mimic function of brain • Underlying technology: a network of “neurons” (nodes) connected by ‘nerves” (edges) • Each has a set of parameters • Each edge is weighted by the relative strength of that connection • Parameters & weights are given values after the network is “trained”

  6. Where can NN be used? • Supervised learning • classification (directed DM) • prediction (directed DM) • Unsupervised learning • clustering (undirected DM) • Self Organizing Map (SOM)

  7. Where can NN be used • real estate appraisal • NN learns by examples • Freddie Mac: Loan Prospector • Fraud detection • Master card • team up with Los Alamos Lab • use state-of-the-art technology that is deployed for military applications • report a saving of more than $50m using the fraud detection system

  8. Where can NN be used? • Direct mail • HNC’s Database Mining Marksman • for one bank, reduce cost by 50%, increase sales by 18% • system costs $48,000 to set up (1995) • financial service customer relationship management (reader) • e-customer relationship management • e.g. HNC, NeoVista, Agnos’s KnowledgeSTUDIO

  9. How does NN work? • A set of inputs (nodes) • A set of outputs (one to a few) • Model biological neurons

  10. How does NN work? • Inputs must be between 0 and 1 • Output is also between 0 and 1 • “Scaling” required for numerical values • (Value - min)/range

  11. How does NN work? • Topology / Architecture • input • output • hidden layer • connection

  12. Architecture of an artificial neural network Input 1 Input 2 Output Input 3 Input Layer Hidden Layer Output Layer

  13. How does NN work? • Action is in hidden layer • Each node combines inputs to give an output

  14. How does NN work? • How to combine? • combination function • transfer function

  15. How does NN work? • Combination function • Put several values into one • weighted sum • maximum

  16. How does NN work? • Transfer function • transfer value of combination function to output (of node) • sigmoid • turn the weighted sum back on 1 to 1 scale

  17. How does NN work? • Training = let it learn from examples • Weights adjusted by procedure calledbackward propagation

  18. How does NN work? • Training & testing sets • Overfitting problem

  19. How does NN work? • Overfit problem • Getting “too close” to data • NN pays attention to noise rather than signal • Result: poor performance when applied to new data set • Remedy: use a separate data set (testing set) to stop training

  20. How does NN work? • Evaluation set • Used for objectively evaluating performance of NN • Misclassification • Discrepancy between what it predicts and what is really observed • Performance metric based on learning sample too optimistic

  21. How does NN work? • Steps in applying NN (p.692) • Transform data • Select architecture • Train and test • Deploy

  22. How does NN work? • Devil is in the details • Training set should cover full range • Topology • Choosing appropriate input variables • e.g. use output from Decision Tree

  23. NN: function approximation • Relate the “inputs” and “outputs” • Mathematically a function approximation problem • NN combines “sigmoids” to produce nonlinear functions of any kind (almost)

  24. Glossary • NN: Neural Network • ANN: Artificial Neural Network • DM: Data Mining • SOM: Self Organizing Maps

More Related