Self-organizing Maps (Kohonen Networks) and related models
-
Upload
oleg-mcguire -
Category
Documents
-
view
48 -
download
0
description
Transcript of Self-organizing Maps (Kohonen Networks) and related models
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 1
Self-organizing MapsSelf-organizing Maps(Kohonen Networks)(Kohonen Networks)and related modelsand related models
Outline:• Cortical Maps• Competitive Learning• Self-organizing Maps (Kohonen Network)• Applications to V1• Contextual Maps• Some Extensions: Conscience, Topology Learning
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 2
Vesalius, 1543
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 3
Brodmann, 1909
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 4
van Essen, 1990s
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 5
Optical imaging of primary visual cortex:orientation selectivity, retinal position, and ocular dominance all mapped onto 2-dim.map.
Somatosensory System:strong magnification of certain body parts “homunculus”
Note: looks at upper layers of cortex
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 6
General ThemesGeneral Themes
Potentially high dimensional inputs are mapped onto two-dimensional cortical surface: dimensionality reduction
Within one column: (from pia to white matter)similar properties of neurons
Cortical Neighbors:smooth changes of properties between neighboring cortical sites
In visual system:Retinotopy dominates: neighboring cortical sites process information from neighboring parts of the retina (the lower in the visual system, the stronger the effect)
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 7
Two ideas for learning mappings:
• Willshaw & von der Malsburg:• discrete input and output space• all-to-all connectivity
• Kohonen:• more abstract formulation• continuous input space• “weight vector” for each output
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 8
Applications of Hebbian Learning:Applications of Hebbian Learning:Retinotopic ConnectionsRetinotopic Connections
retina
tectum
Retinotopic: neighboring retina cells project to neighboring tectum cells,i.e. topology is preserved, hence “retinotopic”
Question: How do retina units know where to project to?Answer: Retina axons find tectum through chemical markers, but finestructure of mapping is activity dependent
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 9
Principal assumptions:- local excitation of neighbors in retina and tectum- global inhibition in both layers-Hebbian learning of feed-forward weights, with constraint on sum of pre-syn. weights- spontaneous activity (blobs) in retina layer
Why should we see retinotopy emerging?
Willshaw & von der Malsburg ModelWillshaw & von der Malsburg Model
tectum
retina
cooperation inintersection area
competition for abilityto innervate tectum area
instability, tectum blob can only form at X or Y
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 10
Hj* = activity in post-synaptic cell j
Ai* = activity of pre-synaptic cell i, either 0 or 1
sij = connection weight from i j
ekj = excitatory connection of post-synaptic cell k post-synaptic cell j
ikj = inhibitory connection of post-synaptic cell k post-synaptic cell j
Weight update: Weight Normalization:
M = # pre cellsN = # post cells
Model EquationsModel Equations
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 11
Results: Systems MatchingResults: Systems Matching
Formation of retinotopic mappings models of this type account for a range of experiments: “half retina”, “half tectum”, “graft rotation”, …
half retina experiment
Retina Tectum
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 12
Simple Competitive LearningSimple Competitive Learning
j
ijiji wwh
define winner: ii hi maxarg*
Assume weights >0 and possibly weights normalized.If weights normalized, hi maximal if wi has smallest Euclideandistance to .
simple linear units,
input is
output of unit:
*:0
:1
ii
iioi
Winner-Take-All Mechanism:may be implemented through lateral inhibition network (see part on Neurodynamics)
“ultra-sparse code”
Figure taken from Hertz et.al.
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 13
)( ijjiij wOw
Weight of winning unit is moved towards current input .Similar to Oja´s and Sanger´s rule.Geometric interpretation: units (their weights) move in input space.Winning unit moves towards current input.
learning rule is Hebb-likeplus decay term
1
2
inputvector
weightvector
normalized weights
Figure taken from Hertz et.al.
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 14
Cost function forCost function forCompetitive LearningCompetitive Learning
)( ijjiij wOw
minimization of sum of squared errors!
Note 1: may be seen as online version of k-means clusteringNote 2: can modify learning rule to make all units fire equally often
otherwise 0
)( if 1
where, 2
1
2
1}{
*
2
,,
2
*
iiM
wMwwE
i
jiijjiiij
Claim: Learning rule related to this cost function:
ijjiij
ij wMw
Ew
To see this, treat M as constant:
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 15
Vector QuantizationVector Quantization
Idea: represent input by weight vector of the winner (can be used for data compression: just store/transmit label representing the winner)
Question: what is set of inputs that “belong” to a unit i, i.e. for which unit i is winner?
Answer: Voroni tesselation (note: matlab command for this)
Figure taken from Hertz et.al.
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 16
Self-Organizing Maps (Kohonen)Self-Organizing Maps (Kohonen)
Idea: Output units have a priori topology (1-dim. or 2-dim.), e.g. are arranged on a chain or regular grid. Not only winner get´s to learn but also its neighbors.
SOMs transform incoming signal patterns of arbitrary dimensionon 1-dim. or 2-dim. map. Neighbors in the map respond to similarinput patterns.
Competition: again with winner-take-all mechanismCooperation: through neighborhood relations that are exploited during learning
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 17
Self-Organizing Maps (Kohonen)Self-Organizing Maps (Kohonen)
Neighboring output units learn together! Update winner’s weightsbut also those of neighbors.
1
2
inputvector
weightvector
example of 1-dim. topology of output nodes
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 18
SOM algorithmSOM algorithm
j
ijiji wwh
Define winner: ii hi maxarg*
again, simple linear units, input is
Output of unit j when winner is i*:
2
2*,
*, 2exp
ij
ij
do
2
*2
*, ijij rrd
,
Usually, neighborhood shrinks with time:(for 0 : competetive learning)
)exp()(1
0 t
t
)(*, jijj wow
Same learning rule as earlier:
Usually, learning rate decays, too: )exp()(2
0 t
t
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 19
2 Learning Phases2 Learning Phases
1. Self-organizing or ordering phase- topological ordering of weight vectors- use: = radius of layer
2. Convergence phase- fine tuning of weights- use: very small neighborhood, learning rate around 0.01
)exp()(2
0 t
t
1000,1.0 20
)exp()(1
0 t
t
0 ,log
1000,
01
time dependenceof parameters: ,
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 20
ExamplesExamples
Figure taken from Haykin
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 21 Figure taken from Haykin
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 22 Figure taken from Hertz et.al.
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 23
Feature Map PropertiesFeature Map Properties
Property 1: feature map approximates the input space
Property 2: topologically ordered, i.e. neighboring units correspond to similar input patterns
Property 3: density matching: density of output units corresponds qualitatively to input probability density function. SOM tends to under-sample high density areas and over-sample low-density areas
Property 4: can be thought of (loosely) as non-linear generalization of PCA.
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 24
Ocular Dominance and Orientation Ocular Dominance and Orientation Tuning in V1Tuning in V1
1. singularities (pinwheels and saddle points) tend to align with centers of ocular dominance bands2. isoorientation contours intersect borders of ocular dominance bandsat approximately 90 deg. angle (“local orthogonality”)3. global disorder: (Mexican-hat like autocorrelation functions)
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 25
SOM model and close relative (elastic net)account for observed structure of pinwheelsand their locations:
10 , )()',()()( 111 rvrrrr ttSOMtt h
zqqyx ),2cos(),2sin(,,
2/'exp)',( 22 rrrr SOMh
))(,(min))(,(' rvrvr r d
SOM based ModelSOM based Model
Obermayer et al.:
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 26
Very similar idea: (Durbin and Mitchinson)
1'
1111 )()'( )(),()()(rr
rrrvvrrr tttttENtt h
zqqyx ),2cos(),2sin(,,
'
122
11 ),'( /2/)(,exp),(r
vrrvvr tENttEN hdh
Elastic Net ModelElastic Net Model
Note: explicitly forces unit’s weight to be similar to that of neighbors
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 27
RF-LISSOM modelRF-LISSOM modelReceptive Field Laterally Interconnected Synergetically Self-Organizing MapReceptive Field Laterally Interconnected Synergetically Self-Organizing Map
Idea: learn RF properties and map simultaneously
Figures taken from http://www.cs.texas.edu/users/nn/web-pubs/htmlbook96/sirosh/
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 28
Lissom equationsLissom equations
input activities are elongated Gaussian blobs:
initial map activity is nonlinear function of input activity, weights μ:
time evolution of activity (μ, E, I are all weights):
Hebbian style learning with weight normalization: all weights learnbut with different parameters:
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 29
Demo: (needssupercomputerpower)
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 30
Contextual MapsContextual Maps
Different way of displaying SOM: label output nodes witha class label describing what output node represents. Can be usedto display data from high dimensional input spaces in 2d.
][ Ta
Ts
T
Input vector is concatenation of attribute vector and symbol code:(symbol code “small” and free of correlations)
Figure takenfrom Haykin
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 31
Contextual Maps cont’d.Contextual Maps cont’d.
Contextual Map trained just like standard SOM.Which unit is winner for symbol input only?
Figure taken from Haykin
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 32
Contextual Maps cont’d.Contextual Maps cont’d.
For which symbol code fires unit the most?
Figure taken from Haykin
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 33
Extension with “Conscience”Extension with “Conscience”
Problem: standard SOM does not faithfully represent input densityMagnification factor: m(x) is the number of units in small volume dx of input space.Ideally:
But this is not what SOM does!
Idea (DeSieno): If neuron wins too often/not often enough,it decreases/increases its chance of winning.(intrinsic plasticity)
)()( xx pm
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 34
Algorithm: SOM with conscience
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 35
Topology Learning: neural gasTopology Learning: neural gasidea: no fixed underlying topology but learn it on-line
Figure taken from Ballard
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 36
Figure taken from Ballard
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 37
SOM SummarySOM Summary
• “simple algorithms” with complex behavior.
• Can be used to understand organization of response preferences for neurons in cortex, i.e. formation of cortical maps.
• Used for visualization of high dimensional data.
• Can be extended for supervised learning.
• Some notable extensions, e.g. neural gas and growing neural gas, that are generalizations to 2-dim topology. Proper (local) topology is discovered during the learning process
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 38
Learning Vector QuantizationLearning Vector Quantization
Idea: supervised add-on for the case that class labels are available for the input vectorsHow it works: first do unsupervised learning, then label output nodes
Learning rule: Cx: desired class label for input x Cw: class label of winning unit with weight vector wIn case Cw=Cx: w=a(t)[x-w] (move weight towards input)In case CwCx: w=-a(t)[x-w] (move away from input)a(t): decaying learning rate Figure taken from Haykin
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 39
LVQdata:
Jochen Triesch, UC San Diego, http://cogsci.ucsd.edu/~triesch 40
LVQresult:
Figure taken from Haykin