260 likes | 358 Vues
Dive into the realm of neural networks and explore their applications in business, from fraud detection to real estate appraisal. Discover how these powerful systems mimic brain functions and learn through examples. Uncover the intricate workings of neural networks, from inputs and outputs to topology and training, revolutionizing industries worldwide. Embrace the future of AI with this comprehensive guide.
E N D
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 • Several generations of ANN • Lab research • Hype : thinking machine • Practical apps in fast chips
NN: Overview • A handwritten recognition example • http://members.aol.com/Trane64/java/JRec.html
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”
Where can NN be used? • Supervised learning • classification (directed DM) • prediction (directed DM) • Unsupervised learning • clustering (undirected DM) • Self Organizing Map (SOM)
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
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
How does NN work? • A set of inputs (nodes) • A set of outputs (one to a few) • Model biological neurons
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
How does NN work? • Topology / Architecture • input • output • hidden layer • connection
Architecture of an artificial neural network Input 1 Input 2 Output Input 3 Input Layer Hidden Layer Output Layer
How does NN work? • Action is in hidden layer • Each node combines inputs to give an output
How does NN work? • How to combine? • combination function • transfer function
How does NN work? • Combination function • Put several values into one • weighted sum • maximum
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
How does NN work? • Training = let it learn from examples • Weights adjusted by procedure calledbackward propagation
How does NN work? • Training & testing sets • Overfitting problem
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
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
How does NN work? • Steps in applying NN (p.692) • Transform data • Select architecture • Train and test • Deploy
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
NN: function approximation • Relate the “inputs” and “outputs” • Mathematically a function approximation problem • NN combines “sigmoids” to produce nonlinear functions of any kind (almost)
Glossary • NN: Neural Network • ANN: Artificial Neural Network • DM: Data Mining • SOM: Self Organizing Maps