190 likes | 610 Views
2. Artificial Intelligence for Data Mining. Neural networks are useful for data mining and decision-support applications.People are good at generalizing from experience.Computers excel at following explicit instructions over and over. Neural networks bridge this gap by modeling, on a computer, the neural behavior of human brains..
E N D
1. Data Mining and Neural Networks
Danny Leung
CS157B, Spring 2006
Professor Sin-Min Lee
2. 2 Artificial Intelligence for Data Mining Neural networks are useful for data mining and decision-support applications.
People are good at generalizing from experience.
Computers excel at following explicit instructions over and over.
Neural networks bridge this gap by modeling, on a computer, the neural behavior of human brains.
3. 3 Neural Network Characteristics
Neural networks are useful for pattern recognition or data classification, through a learning process.
Neural networks simulate biological systems, where learning involves adjustments to the synaptic connections between neurons
4. 4 Anatomy of a Neural Network
Neural Networks map a set of input-nodes to a set of output-nodes
Number of inputs/outputs is variable
The Network itself is composed of an arbitrary number of nodes with an arbitrary topology
5. 5 Biological Background 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
6. 6 Basics of a Node A node is an element which performs a function
y = fH(?(wixi) + Wb)
7. 7 A Simple Preceptron Binary logic application
fH(x) [linear threshold]
Wi = random(-1,1)
Y = u(W0X0 + W1X1 + Wb)
8. 8 Preceptron Training It’s a single-unit network
Adjust weights based on a how well the current weights match an objective
Perceptron Learning Rule
? Wi = ? * (D-Y).Ii
? = Learning Rate
D = Desired Output
9. 9 Neural Network Learning From experience: examples / training data
Strength of connection between the neurons is stored as a weight-value for the specific connection
Learning the solution to a problem = changing the connection weights
10. 10 Neural Network Learning Continuous Learning Process
Evaluate output
Adapt weights
Take new inputs
Learning causes stable state of the weights
11. 11 Learning Performance Supervised
Need to be trained ahead of time with lots of data
Unsupervised networks adapt to the input
Applications in Clustering and reducing dimensionality
Learning may be very slow
No help from the outside
No training data, no information available on the desired output
Learning by doing
Used to pick out structure in the input:
Clustering
Compression
12. 12 Topologies – Back-Propogated Networks Inputs are put through a ‘Hidden Layer’ before the output layer
All nodes connected between layers
13. 13 BP Network – Supervised Training
Desired output of the training examples
Error = difference between actual & desired output
Change weight relative to error size
Calculate output layer error , then propagate back to previous layer
Hidden weights updated
Improved performance
14. 14 Neural Network Topology Characteristics
Set of inputs
Set of hidden nodes
Set of outputs
Increasing nodes makes network more difficult to train
15. 15 Applications of Neural Networks Prediction – weather, stocks, disease
Classification – financial risk assessment, image processing
Data association – Text Recognition (OCR)
Data conceptualization – Customer purchasing habits
Filtering – Normalizing telephone signals (static)
16. 16 Overview Advantages
Adapt to unknown situations
Robustness: fault tolerance due to network redundancy
Autonomous learning and generalization
Disadvantages
Not exact
Large complexity of the network structure
17. 17 Referenced Work Intro to Neural Networks - Computer Vision Applications and Training Techniques. Doug Gray. www.soe.ucsc.edu/~taoswap/ GroupMeeting/NN_Doug_2004_12_1.ppt
Introduction to Artificial Neural Networks. Nicolas Galoppo von Borries. www.cs.unc.edu/~nico/courses/ comp290-58/nn-presentation/ann-intro.ppt