Software Simulation of a Self-organizing Learning Array System - PowerPoint PPT Presentation

Loading...

PPT – Software Simulation of a Self-organizing Learning Array System PowerPoint presentation | free to download - id: 66dd11-NGQwM



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

Software Simulation of a Self-organizing Learning Array System

Description:

Software Simulation of a Self-organizing Learning Array System Janusz Starzyk & Zhen Zhu School of EECS Ohio University Theme SOLAR = Self-organizing Learning Array ... – PowerPoint PPT presentation

Number of Views:5
Avg rating:3.0/5.0
Slides: 24
Provided by: zhuz6
Learn more at: http://www.ohio.edu
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: Software Simulation of a Self-organizing Learning Array System


1
Software Simulation of a Self-organizing
Learning Array System
  • Janusz Starzyk Zhen Zhu
  • School of EECS
  • Ohio University

2
Theme
  • SOLAR Self-organizing Learning Array
  • Introduction to SOLAR
  • Software simulation
  • Performance of SOLAR

3
Introduction to SOLAR
  • SOLAR
  • Artificial neural networks (ANN)
  • Self-organizing structure
  • Re-configurable hardware

4
Introduction to SOLAR
  • Basic frame of SOLAR
  • A fixed lattice of processing units (neurons)
  • Self-organization
  • Interconnections among the units refined during
    learning

5
Software Simulation - SOLAR
  • Simulation tasks
  • Pre-processing of input data to SOLAR
  • Behavior of a single neuron
  • Network structure
  • Classification
  • Assembly of various networks

6
Software Simulation - SOLAR
  • Inputs outputs of SOLAR

7
Software Simulation - SOLAR
  • Real world input data features X
  • Incomplete set data missing
  • Symbolic unacceptable to neural computation
  • Unbalance weighted needs to be equalized
  • Pre-processing
  • Calculate default substitutes for missing data
  • Set continuous values to all symbols
  • Rescaling

8
Software Simulation - SOLAR
  • Missing data problem
  • Find defaults for missing items in each
    individual inputs to minimize Mahalanobis
    distance.
  • Separate known items Xk, and missing items Xm
    XXk, Xm.
  • Compute covariance matrix and its inversed
    matrix .
  • Partition matrix .
  • Compute default Xm

9
Software Simulation - SOLAR
  • Inputs outputs of a single SOLAR neuron

10
Software Simulation - SOLAR
  • Behavior of a single SOLAR neuron
  • Output behaves a selected functions of input.
  • Unary input operations OY(I1) or OY(I2).
  • Binary input operations OY(I1, I2).
  • All the operations are redesigned arithmetic
    operations.
  • -Linear/ non-linear
  • -Input/output range is set as 0-255.

11
Software Simulation - SOLAR
  • Unary input operations
  • Identical function YIDENT(x)
  • Half function YHALF(x)
  • Logarithm function
  • YNLOG2(x)
  • Exponential functionY NEXP2(x)
  • Binary input operations
  • Addition function YNADD(x1,x2)
  • Subtraction function YNSUB(x1,x2)

12
Software Simulation - SOLAR
  • Example YNLOG2(x)

13
Software Simulation - SOLAR
  • HOW does a neuron learn from training data and
    process on testing data?
  • Each neuron chooses an operation and a
    threshold. The whole input space will be cut into
    2 parts (subspaces).
  • Ex

14
Software Simulation - SOLAR
  • Neuron learning
  • Neurons learn from each other and generates more
    complicated cuttings.

15
Software Simulation - SOLAR
  • Neuron learning
  • In order to effectively separate different
    classes, a neuron may choose from different
    configure options.

1 function and 1 threshold are selected
processing unit
Input clock 1 2 3
16
Software Simulation - SOLAR
  • Classification
  • On each individual testing input data point, some
    of or all the neurons are active in
    classification.
  • Neurons are activated with input clocks.
  • Each neuron saves classification probabilities
    based on subspace division.
  • Ex subspace 1 subspace 2
  • class 1 60 10
  • class 2 10 80
  • class 3 30 10

17
Software Simulation - SOLAR
  • Classification
  • On each testing input data point, some neurons
    have sufficient knowledge from learning and
    become eligible.
  • They vote on the classification of this point.

18
Software Simulation - SOLAR
  • Classification
  • Several independent SOLAR networks form an
    ensemble to vote on the same problem.

19
Performance Evaluation - SOLAR
  • An Australian credit card data set 1 is used to
    evaluate SOLAR performance.
  • 14 input features, 690 individuals, 2 classes
  • This data set is a typical classification problem
    and has been used to test other classic
    classification algorithms 2.

20
Performance Evaluation - SOLAR
  • Divide the data set into 10 groups randomly.
  • Run the simulation 10 times.
  • Each time use 1 group for testing the the
    remaining for training.
  • Average the resultant classification rate.
  • Experimented on single SOLAR and SOLAR ensemble.

21
Performance Evaluation - SOLAR
22
Performance Evaluation - SOLAR
  • Conclusion
  • Although SOLAR was not designed with any
    particular purposes, it works well with several
    classification problems.
  • SOLAR behaviors are observed in this simulation.

23
References
  • 1 Y. Liu, X. Yao and T. Higuchi, Evolutionary
    Ensembles with Negative Correlation Learning,
    IEEE Trans. on Evolutionary Computation, Vol. 4,
    No. 4, Nov 2000.
  • 2 D. Michie, D. J. Spiegelhalter, and C. C.
    Taylor, Machine Learning, Neural and Statistical
    Classification London, U. K. Ellis Horwood Ltd.
    1994
About PowerShow.com