Transcript Document
Un Supervised Learning & Self Organizing Maps
Un Supervised Competitive Learning
• In Hebbian networks, all neurons can fire at the same time • Competitive learning means that only a single neuron from each group fires at each time step • Output units compete with one another. • These are
winner takes all
( grandmother cells ) units
UnSupervised Competitive Learning
• In the hebbian like models, all the neurons can fire together • In
Competitive Learning
models, only one unit (or one per group) can fire at a time • Output units compete with one another
Winner Takes All
units (“grandmother cells”)
US Competitive, Cntd
• Such networks cluster the data points • The number of clusters is not predefined but is limited to the number of output units • Applications include VQ, medical diagnosis, document classification and more
Simple Competitive Learning
N inputs units P output neurons P x N weights
h i
i
1 , 2 ...
P j N
1
W ij X j
x 1 x 2
Y i
1 or 0 x N W P1 W 11 W 12 W 22 W PN Y 1 Y 2 Y P
Simple Model, Cntd
• All weights are positive and normalized • Inputs and outputs are binary
i h
*
i
W ij j
arg
X j
max(
h i
W i
)
X
Network Activation
• The unit with the highest field
h
i
fires •
i*
is the winner unit
W i
* input vector • The winning unit’s weight vector is updated to be even closer to the current input vector • Possible variation: adding lateral inhibition
Learning
Starting with small random weights, at each step: 1. a new input vector is presented to the network 2. all fields are calculated to find a winner 3.
W i
* is updated to be closer to the input
Learning Rule
•
Standard Competitive Learning
W i
*
j
(
X j
W i
*
j
) Can be formulated as hebbian :
W ij
O i
(
X j
W ij
)
Result
• Each output unit moves to the center of mass of a cluster of input vectors
clustering
Competitive Learning, Cntd
• It is important to break the symmetry in the initial random weights • Final configuration depends on initialization – A winning unit has more chances of winning the next time a similar input is seen – Some outputs may never fire – This can be compensated by updating the non winning units with a smaller update
Model: Horizontal & Vertical lines
Rumelhart & Zipser, 1985 • Problem – identify vertical or horizontal signals • Inputs are 6 x 6 arrays • Intermediate layer with 8 WTA units • Output layer with 2 WTA units • Cannot work with one layer
Rumelhart & Zipser, Cntd H V
Geometrical Interpretation
• So far the ordering of the output units themselves was not necessarily informative • The location of the winning unit can give us information regarding similarities in the data • We are looking for an input output mapping that
conserves the topologic properties
feature mapping
of the inputs • Given any two spaces, it is not guaranteed that such a mapping exits!
Biological Motivation
• In the brain, sensory inputs are represented by topologically ordered computational maps – Tactile inputs – Visual inputs (center-surround, ocular dominance, orientation selectivity) – Acoustic inputs
Biological Motivation, Cntd
• Computational maps are a basic building block of sensory information processing • A computational map is an array of neurons representing slightly different tuned processors (filters) that operate
in parallel
on sensory signals • These neurons transform input signals into a
place coded structure
Self Organizing (Kohonen) Maps
• Competitive networks (WTA neurons) • Output neurons are placed on a lattice, usually 2 dimensional • Neurons become
selectively tuned
patterns (stimuli) to various input • The location of the tuned (winning) neurons become ordered in such a way that creates a
meaningful coordinate system
features for different input a
topographic map
of input patterns is formed
SOMs, Cntd
• Spatial locations of the neurons in the map are indicative of statistical features that are present in the inputs (stimuli)
Self Organization
Kohonen Maps
• Simple case: 2-d input and 2-d output layer • No lateral connections • Weight update is done for the winning neuron and
its surrounding neighborhood
W ij
F (
i
,
i
*)(
X
j
W ij
)
Neighborhood Function
• F is maximal for
i
* and drops to zero far from
i
, for example: F
(i,i*)
exp(
r
i
2
r
i
* 2 2 ) • The update “pulls” the winning unit (weight vector) to be closer to the input, and also drags the close neighbors of this unit
• The output layer is a sort of an
elastic net
that wants to come as close as possible to the inputs • The output maps conserves the
topological relationships
of the inputs • Both η and σ can be changed during the learning
Feature Mapping
Weight Vectors Weight Vectors 6 6 3 4 4 2 2 2 1 0 0 0 -2 -2 -1 -4 -4 -2 -6 -6 -3 -4 -4 -6 -4 -2 -2 -4 -2 0 0 0 2 2 4 4 6 6 6 8 8 8 10 10 10 12 12 12 14
Topologic Maps in the Brain
• Examples of topologic conserving mapping between input and output spaces – Retintopoical mapping between the retina and the cortex – Ocular dominance – Somatosensory mapping (the homunculus)
Models
Goodhill (1993) proposed a model for the development of retinotopy and ocular dominance, based on Kohonen Maps – Two retinas project to a single layer of cortical neurons – Retinal inputs were modeled by random dots patterns – Added between eyes correlation in the inputs – The result is an ocular dominance map and a retinotopic map as well
Models, Cntd
Farah (1998) proposed an explanation for the spatial ordering of the
homunculus
using a simple SOM.
– In the womb, the fetus lies with its hands close to its face, and its feet close to its genitals – This should explain the order of the somatosensory areas in the
homunculus
Other Models
• Semantic self organizing maps to model language acquisition • Kohonen feature mapping to model layered organization in the LGN • Combination of unsupervised and supervised learning to model complex computations in the visual cortex
Examples of Applications
• Kohonen (1984). Speech recognition - a map of phonemes in the Finish language • Optical character recognition - clustering of letters of different fonts • Angeliol
etal
(1988) – travelling salesman problem (an optimization problem) • Kohonen (1990) – learning vector quantization (pattern classification problem) • Ritter & Kohonen (1989) – semantic maps
Summary
• Unsupervised learning is very common • US learning requires redundancy in the stimuli • Self organization is a basic property of the brain’s computational structure • SOMs are based on – competition (wta units) – cooperation – synaptic adaptation • SOMs conserve topological relationships between the stimuli • Artificial SOMs have many applications in computational neuroscience