Scribd
Upload
44 views14 pages

Intro to Self-Organizing Maps

This document discusses self-organizing maps (SOMs), an unsupervised neural network technique that maps multidimensional data onto a 2D grid so that similar inputs are represented by nearby neurons. It describes the SOM algorithm, which initializes neuron weights randomly or pregenerated and iteratively adjusts the weights of the winning neuron and its neighbors based on input. Optimization techniques like reducing dimensionality and pregenerating weights are also covered. Current applications mentioned include organizing document collections, phonetic typing, and poverty classification. The document concludes with details about an accompanying demo program.

Uploaded by

Medhavi Mahobe
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
44 views14 pages

Intro to Self-Organizing Maps

This document discusses self-organizing maps (SOMs), an unsupervised neural network technique that maps multidimensional data onto a 2D grid so that similar inputs are represented by nearby neurons. It describes the SOM algorithm, which initializes neuron weights randomly or pregenerated and iteratively adjusts the weights of the winning neuron and its neighbors based on input. Optimization techniques like reducing dimensionality and pregenerating weights are also covered. Current applications mentioned include organizing document collections, phonetic typing, and poverty classification. The document concludes with details about an accompanying demo program.

Uploaded by

Medhavi Mahobe
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 14

Self-organizing Maps

Kevin Pang

Goal

Research SOMs Create an introductory tutorial on the algorithm Advantages / disadvantages Current applications Demo program

Self-organizing Maps

Unsupervised learning neural network Maps multidimensional data onto a 2 dimensional grid Geometric relationships between image points indicate similarity

Algorithm

Neurons arranged in a 2 dimensional grid Each neuron contains a weight vector

Example: RGB values

Algorithm (continued)

Initialize weights
Random Pregenerated

Iterate through inputs For each input, find the winning neuron

Euclidean distance

Adjust winning neuron and its neighbors


Gaussian Mexican hat

Optimization Techniques

Reducing input / neuron dimensionality

Random Projection method


Initialize map closer to final state Reduce the amount of exhaustive searches

Pregenerating neuron weights

Restricting winning neuron search

Conclusions

Advantages
Data mapping is easily interpreted Capable of organizing large, complex data sets

Disadvantages
Difficult to determine what input weights to use Mapping can result in divided clusters Requires that nearby points behave similarly

Current Applications

WEBSOM: Organization of a Massive Document Collection

Current Applications (continued)

Phonetic Typewriter

Current Applications (continued)

Classifying World Poverty

Demo Program

Written for Windows with GLUT support Demonstrates the SOM training algorithm in action

Demo Program Details

Randomly initialized map 100 x 100 grid of neurons, each containing a 3dimensional weight vector representing its RGB value Training input randomly selected from 48 unique colors Gaussian neighborhood function

Screenshots

Questions?

You might also like