SlideShare a Scribd company logo
1 of 20
Download to read offline
Self Organising Neural Networks




   Kohonen Networks.
   A Problem with Neural Networks.
   ART.


Beal, R. and Jackson, T. (1990). Neural Computing: An Introduction.
   Chapters 5 & 7. Adam Hilger, NY.
Hertz, J., Krogh, A. and Palmer, R. (1991). Introduction to the Theory
   of Neural Computation. Chapter 9. Addison–Wesley. NY.
Grossberg, S. (1987). Competitive Learning: from interactive acti-
   vation to adaptive resonance. Cognitive Science, 11: 23–63.




                                  1
Kohonen Self Organising Networks



Kohonen, T. (1982). Self–organized formation of topologically cor-
rect feature maps., Biological Cybernetics, 43: 59–69.

    An abstraction from earlier models (e.g. Malsburg,
    1973).
    The formation of feature maps (introducing a geo-
    metric layout).
    Popular and useful.
    Can be traced to biologically inspired origins.
    Why have topographic mappings?

      – Minimal wiring
      – Help subsequent processing layers.

    Example: Xenopus retinotectal mapping (Price & Will-
    shaw 2000, p121).




                                   2
Basic Kohonen Network




  Geometric arrangement of units.
  Units respond to “part” of the environment.
  Neighbouring units should respond to similar parts
  of the environment.
  Winning unit selected by:
                Ü Û           min   Ü Û
  where Û is the weight vector of winning unit, and
  Ü is the input pattern.
  and Neighbourhoods...




                          3
Neighbourhoods in the Kohonen Network




  Example in 2D.




  Neighbourhood of winning unit called Æ .




                       4
Learning in the Kohonen Network




  All units in Æ are updated.
        dÛ            ´ µ ´ µ   Û ´Øµ
                  « Ø Ü Ø               for ¾ Æ
         dØ       ¼                     otherwise
  where
      dÛ
       dØ = change in weight over time.
       ´µ
      « Ø = time dependent learning parameter.
      Ü ´Øµ = input component at time Ø.
      Û ´Øµ = weight from input to unit     at time Ø.
 ¯ Geometrical effect: move weight vector closer to in-
   put vector.
 ¯ « is strongest for winner and can decrease with dis-
   tance. Also decreases over time for stability.




                            5
Biological origins of the Neighbourhoods




   Lateral interaction of the units.
   Mexican Hat form:

                    1.6

                    1.4

                    1.2

                      1

                    0.8

                    0.6

                    0.4

                    0.2

                      0

                    -0.2

                    -0.4
                      -100      -80        -60        -40       -20       0   20   40        60   80    100




                3



                2



                1



                0



               -1
               40
                           30                                                                                 40
                                      20                                                           30
                                                                                        20
                                                 10
                                                                              10
                                                                0     0




                                                            6
Biological origins of the Neighbourhoods: Mals-
burg




   Excitatory connections:

                                         Excitatory units




                                         Inhibitory units

   Inhibitory connections:

                                         Excitatory units




                                         Inhibitory units

Implements winner-take-all processing.




                             7
1-d example

                                  4
                                               3
                                                       2
                              1
                                               5


                                  4
                                                   3
                                                       2
                                              1
                                          5




                  4
                                  3                    2
                          5                   1




                      5       4
                                      3   2 1




              5
                      4

                                      3   2 1




                                  8
2-d example: uniform density




   8x8 units in 2D lattice




   2 input lines.
   Inputs between ·½ and  ½.
   Input space:


                                 +1




                      -1              +1




                                 -1




                             9
2-d example: uniform density




                     10
2-d example: non-uniform density




  Same 8x8 units in 2D lattice.
  Same input space.
  Different input distribution


                                 +1




                      -1              +1




                                 -1




                           11
2-d example: non-uniform density




                     12
2-d   µ 1-d example: dimension reduction

  2-d input uniform density; 1-d output arrangement.
  “Space-filling” (Peano) curves; can solve Travelling
  Salesman Problem.

                init wts                   epoch 10




              epoch 500                   epoch 700




                           13
Example Application of Kohonen’s Network



The Phonetic Typewriter
     MP     Filter        A/D




                                 FFT




    Rules


                                           Kohonen
                                           Network




   Problem: Classification of phonemes in real time.
   Pre and post processing.
   Network trained on time sliced speech wave forms.
   Rules needed to handle co-articulation effects.




                          14
A Problem with Neural Networks



Consider 3 network examples:

   Kohonen Network.
   Associative Network.
   Feed Forward Back-propagation.

Under the situation:

   Network learns environment (or I/O relations).
   Network is stable in the environment.
   Network is placed in a new environment.

What happens:

   Kohonen Network won’t learn.
   Associative Network OK.
   Feed Forward Back-propagation Forgets.

called The Stability/Plasticity Dilemma.




                          15
Adaptive Resonance Theory



Grossberg, S. (1976a). Adaptive pattern classification and univer-
sal recoding I: Feedback, expectation, olfaction, illusions. Biological
Cybernetics, 23: 187–202.

    a “neural network that self–organize[s] stable pat-
    tern recognition codes in real time, in response to
    arbitrary sequences of input patterns”.

    ART1 (1976). Localist representation, binary patterns.
    ART2 (1987). Localist representation, analog patterns.
    ART3 (1990). Distributed representation, analog pat-
    terns.
    Desirable properties:
         plastic + stable
         biological mechanisms
         analytical math foundation




                                  16
ART1




                   Attentional subsystem

                     F2 units ( )




                                                      Orienting subsystem
                     + (Ø )        +(   )
 -
         +          F1 units (Ü )             -   r
     G

 +                                                +
                              +


                         Input (Ü )

     F1  F2 fully connected, excitatory (    ).
     F2  F1 fully connected, excitatory (Ø ).
     Pattern of activation on F1 and F2 called Short Term
     Memory.
     Weight representations called Long Term Memory.
     Localist representations of binary input patterns.




                                  17
Summary of ART 1

        (Lippmann, 1987). N = number of F1 units.
Step 1: Initialization
                                            Ø                ½            ½
                                                                         ½·Æ
               Set vigilance parameter                           ¼             ½
Step 2: apply new input (binary Ü )
Step 3: compute F2 activation
                                            Æ

                                                         Ü
                                             ½

Step 4: find best matching node , where                                             .
Step 5: vigilance test
                          Æ                                          Æ

                                  Ü         Ì    ¡                       Ø Ü
                              ½                                      ½
                              Ì   ¡
                     Is

        If no, go to step 6. If yes go to step 7.
Step 6: mismatch/reset: set                 ¼ and go to step 4.
Step 7: resonance — adapt best match
                          Ø           Ø Ü
                                                 Ø
                                        ·
                                            È        Æ
                                                         ½Ø      Ü

Step 8: Re-enable all F2 units and go to step 2

                                       18
ART1: Example



      INPUT   F2 UNITS REPRESENT:
              UNIT 1       UNIT 2           UNIT 3       UNIT 4       UNIT 5




              resonance




              resonance




              1st choice   resonance
              reset




              2nd choice   1st choice       resonance
              reset        reset




              3rd choice   1st choice       2nd choice   resonance
              reset        reset            reset




              1st choice
              resonance




                           1st choice                    2nd choice
                           reset                         resonance




              1st choice   4th choice       3rd choice   2nd choice   resonance
              reset        reset            reset        reset




                                       19
Summary




  Simple?
  Interesting biological parallels.
  Diverse applications.
  Extensions.




                           20

More Related Content

What's hot

On Approach to Increase Integration Rate of Elements of a Current Source Circuit
On Approach to Increase Integration Rate of Elements of a Current Source CircuitOn Approach to Increase Integration Rate of Elements of a Current Source Circuit
On Approach to Increase Integration Rate of Elements of a Current Source CircuitBRNSS Publication Hub
 
BINARY TREE SORT IS MORE ROBUST THAN QUICK SORT IN AVERAGE CASE
BINARY TREE SORT IS MORE ROBUST THAN QUICK SORT IN AVERAGE CASEBINARY TREE SORT IS MORE ROBUST THAN QUICK SORT IN AVERAGE CASE
BINARY TREE SORT IS MORE ROBUST THAN QUICK SORT IN AVERAGE CASEIJCSEA Journal
 
Finite element analysis of space truss by abaqus
Finite element analysis of space truss by abaqus Finite element analysis of space truss by abaqus
Finite element analysis of space truss by abaqus P Venkateswalu
 
Constant strain triangular
Constant strain triangular Constant strain triangular
Constant strain triangular rahul183
 
International journal of engineering issues vol 2015 - no 2 - paper5
International journal of engineering issues   vol 2015 - no 2 - paper5International journal of engineering issues   vol 2015 - no 2 - paper5
International journal of engineering issues vol 2015 - no 2 - paper5sophiabelthome
 
AN APPROACH TO OPTIMIZE MANUFACTURE OF AN ACTIVE QUADRATURE SIGNAL GENERATOR ...
AN APPROACH TO OPTIMIZE MANUFACTURE OF AN ACTIVE QUADRATURE SIGNAL GENERATOR ...AN APPROACH TO OPTIMIZE MANUFACTURE OF AN ACTIVE QUADRATURE SIGNAL GENERATOR ...
AN APPROACH TO OPTIMIZE MANUFACTURE OF AN ACTIVE QUADRATURE SIGNAL GENERATOR ...antjjournal
 
S.Duplij, R.Vogl, "Membership amplitudes and obscure qudits", arXiv:2011.04370
S.Duplij, R.Vogl, "Membership amplitudes and obscure qudits", arXiv:2011.04370 S.Duplij, R.Vogl, "Membership amplitudes and obscure qudits", arXiv:2011.04370
S.Duplij, R.Vogl, "Membership amplitudes and obscure qudits", arXiv:2011.04370 Steven Duplij (Stepan Douplii)
 
Exploring temporal graph data with Python: 
a study on tensor decomposition o...
Exploring temporal graph data with Python: 
a study on tensor decomposition o...Exploring temporal graph data with Python: 
a study on tensor decomposition o...
Exploring temporal graph data with Python: 
a study on tensor decomposition o...André Panisson
 
Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkHiroshi Kuwajima
 
Simple Comparison of Convergence of GeneralIterations and Effect of Variation...
Simple Comparison of Convergence of GeneralIterations and Effect of Variation...Simple Comparison of Convergence of GeneralIterations and Effect of Variation...
Simple Comparison of Convergence of GeneralIterations and Effect of Variation...Komal Goyal
 
Illustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
Illustration Clamor Echelon Evaluation via Prime Piece PsychotherapyIllustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
Illustration Clamor Echelon Evaluation via Prime Piece PsychotherapyIJMER
 
Free vibration analysis of composite plates with uncertain properties
Free vibration analysis of composite plates  with uncertain propertiesFree vibration analysis of composite plates  with uncertain properties
Free vibration analysis of composite plates with uncertain propertiesUniversity of Glasgow
 
Wavelets for computer_graphics_stollnitz
Wavelets for computer_graphics_stollnitzWavelets for computer_graphics_stollnitz
Wavelets for computer_graphics_stollnitzJuliocaramba
 
A study on singular perturbation correction to bond prices under affine term ...
A study on singular perturbation correction to bond prices under affine term ...A study on singular perturbation correction to bond prices under affine term ...
A study on singular perturbation correction to bond prices under affine term ...Frank Fung
 
Generalization of Compositons of Cellular Automata on Groups
Generalization of Compositons of Cellular Automata on GroupsGeneralization of Compositons of Cellular Automata on Groups
Generalization of Compositons of Cellular Automata on GroupsYoshihiro Mizoguchi
 
Fractal Image Compression By Range Block Classification
Fractal Image Compression By Range Block ClassificationFractal Image Compression By Range Block Classification
Fractal Image Compression By Range Block ClassificationIRJET Journal
 
Free vibration analysis of laminated composite beams using fem
Free vibration analysis of laminated composite beams using femFree vibration analysis of laminated composite beams using fem
Free vibration analysis of laminated composite beams using femOsama Mohammed Elmardi Suleiman
 

What's hot (20)

support vector machine
support vector machinesupport vector machine
support vector machine
 
On Approach to Increase Integration Rate of Elements of a Current Source Circuit
On Approach to Increase Integration Rate of Elements of a Current Source CircuitOn Approach to Increase Integration Rate of Elements of a Current Source Circuit
On Approach to Increase Integration Rate of Elements of a Current Source Circuit
 
BINARY TREE SORT IS MORE ROBUST THAN QUICK SORT IN AVERAGE CASE
BINARY TREE SORT IS MORE ROBUST THAN QUICK SORT IN AVERAGE CASEBINARY TREE SORT IS MORE ROBUST THAN QUICK SORT IN AVERAGE CASE
BINARY TREE SORT IS MORE ROBUST THAN QUICK SORT IN AVERAGE CASE
 
Finite element analysis of space truss by abaqus
Finite element analysis of space truss by abaqus Finite element analysis of space truss by abaqus
Finite element analysis of space truss by abaqus
 
Constant strain triangular
Constant strain triangular Constant strain triangular
Constant strain triangular
 
International journal of engineering issues vol 2015 - no 2 - paper5
International journal of engineering issues   vol 2015 - no 2 - paper5International journal of engineering issues   vol 2015 - no 2 - paper5
International journal of engineering issues vol 2015 - no 2 - paper5
 
AN APPROACH TO OPTIMIZE MANUFACTURE OF AN ACTIVE QUADRATURE SIGNAL GENERATOR ...
AN APPROACH TO OPTIMIZE MANUFACTURE OF AN ACTIVE QUADRATURE SIGNAL GENERATOR ...AN APPROACH TO OPTIMIZE MANUFACTURE OF AN ACTIVE QUADRATURE SIGNAL GENERATOR ...
AN APPROACH TO OPTIMIZE MANUFACTURE OF AN ACTIVE QUADRATURE SIGNAL GENERATOR ...
 
S.Duplij, R.Vogl, "Membership amplitudes and obscure qudits", arXiv:2011.04370
S.Duplij, R.Vogl, "Membership amplitudes and obscure qudits", arXiv:2011.04370 S.Duplij, R.Vogl, "Membership amplitudes and obscure qudits", arXiv:2011.04370
S.Duplij, R.Vogl, "Membership amplitudes and obscure qudits", arXiv:2011.04370
 
Exploring temporal graph data with Python: 
a study on tensor decomposition o...
Exploring temporal graph data with Python: 
a study on tensor decomposition o...Exploring temporal graph data with Python: 
a study on tensor decomposition o...
Exploring temporal graph data with Python: 
a study on tensor decomposition o...
 
Capstone paper
Capstone paperCapstone paper
Capstone paper
 
Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural Network
 
Simple Comparison of Convergence of GeneralIterations and Effect of Variation...
Simple Comparison of Convergence of GeneralIterations and Effect of Variation...Simple Comparison of Convergence of GeneralIterations and Effect of Variation...
Simple Comparison of Convergence of GeneralIterations and Effect of Variation...
 
Illustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
Illustration Clamor Echelon Evaluation via Prime Piece PsychotherapyIllustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
Illustration Clamor Echelon Evaluation via Prime Piece Psychotherapy
 
Free vibration analysis of composite plates with uncertain properties
Free vibration analysis of composite plates  with uncertain propertiesFree vibration analysis of composite plates  with uncertain properties
Free vibration analysis of composite plates with uncertain properties
 
Wavelets for computer_graphics_stollnitz
Wavelets for computer_graphics_stollnitzWavelets for computer_graphics_stollnitz
Wavelets for computer_graphics_stollnitz
 
A study on singular perturbation correction to bond prices under affine term ...
A study on singular perturbation correction to bond prices under affine term ...A study on singular perturbation correction to bond prices under affine term ...
A study on singular perturbation correction to bond prices under affine term ...
 
Generalization of Compositons of Cellular Automata on Groups
Generalization of Compositons of Cellular Automata on GroupsGeneralization of Compositons of Cellular Automata on Groups
Generalization of Compositons of Cellular Automata on Groups
 
Fractal Image Compression By Range Block Classification
Fractal Image Compression By Range Block ClassificationFractal Image Compression By Range Block Classification
Fractal Image Compression By Range Block Classification
 
Free vibration analysis of laminated composite beams using fem
Free vibration analysis of laminated composite beams using femFree vibration analysis of laminated composite beams using fem
Free vibration analysis of laminated composite beams using fem
 
Aleksander gegov
Aleksander gegovAleksander gegov
Aleksander gegov
 

Similar to Self Organinising neural networks

Distilling Free-Form Natural Laws from Experimental Data
Distilling Free-Form Natural Laws from Experimental DataDistilling Free-Form Natural Laws from Experimental Data
Distilling Free-Form Natural Laws from Experimental Dataswissnex San Francisco
 
Wavelet transform and its applications in data analysis and signal and image ...
Wavelet transform and its applications in data analysis and signal and image ...Wavelet transform and its applications in data analysis and signal and image ...
Wavelet transform and its applications in data analysis and signal and image ...Sourjya Dutta
 
Network Identification via Node Knock-out
Network Identification via Node Knock-outNetwork Identification via Node Knock-out
Network Identification via Node Knock-outMarzieh Nabi
 
The Back Propagation Learning Algorithm
The Back Propagation Learning AlgorithmThe Back Propagation Learning Algorithm
The Back Propagation Learning AlgorithmESCOM
 
Adobe AIR: Stage3D and AGAL
Adobe AIR: Stage3D and AGALAdobe AIR: Stage3D and AGAL
Adobe AIR: Stage3D and AGALDaniel Freeman
 
Condition Monitoring Of Unsteadily Operating Equipment
Condition Monitoring Of Unsteadily Operating EquipmentCondition Monitoring Of Unsteadily Operating Equipment
Condition Monitoring Of Unsteadily Operating EquipmentJordan McBain
 
Application of differentiation
Application of differentiationApplication of differentiation
Application of differentiationLily Maryati
 
Friedlander et al. Evolution of Bow-Tie Architectures in Biology (2015)
Friedlander et al. Evolution of Bow-Tie Architectures in Biology (2015)Friedlander et al. Evolution of Bow-Tie Architectures in Biology (2015)
Friedlander et al. Evolution of Bow-Tie Architectures in Biology (2015)Thoma Itoh
 
Cauchy’s Inequality based study of the Differential Equations and the Simple ...
Cauchy’s Inequality based study of the Differential Equations and the Simple ...Cauchy’s Inequality based study of the Differential Equations and the Simple ...
Cauchy’s Inequality based study of the Differential Equations and the Simple ...IRJET Journal
 
Session02 review-laplace and partial fractionl
Session02 review-laplace and partial fractionlSession02 review-laplace and partial fractionl
Session02 review-laplace and partial fractionlAhmad Essam
 
Signal Processing Course : Wavelets
Signal Processing Course : WaveletsSignal Processing Course : Wavelets
Signal Processing Course : WaveletsGabriel Peyré
 
Puzzle-Based Automatic Testing: Bringing Humans Into the Loop by Solving Puzz...
Puzzle-Based Automatic Testing: Bringing Humans Into the Loop by Solving Puzz...Puzzle-Based Automatic Testing: Bringing Humans Into the Loop by Solving Puzz...
Puzzle-Based Automatic Testing: Bringing Humans Into the Loop by Solving Puzz...Sung Kim
 
Integrability and weak diffraction in a two-particle Bose-Hubbard model
 Integrability and weak diffraction in a two-particle Bose-Hubbard model  Integrability and weak diffraction in a two-particle Bose-Hubbard model
Integrability and weak diffraction in a two-particle Bose-Hubbard model jiang-min zhang
 
Geohydrology ii (3)
Geohydrology ii (3)Geohydrology ii (3)
Geohydrology ii (3)Amro Elfeki
 

Similar to Self Organinising neural networks (20)

Distilling Free-Form Natural Laws from Experimental Data
Distilling Free-Form Natural Laws from Experimental DataDistilling Free-Form Natural Laws from Experimental Data
Distilling Free-Form Natural Laws from Experimental Data
 
Wavelet transform and its applications in data analysis and signal and image ...
Wavelet transform and its applications in data analysis and signal and image ...Wavelet transform and its applications in data analysis and signal and image ...
Wavelet transform and its applications in data analysis and signal and image ...
 
Lecture.1
Lecture.1Lecture.1
Lecture.1
 
Network Identification via Node Knock-out
Network Identification via Node Knock-outNetwork Identification via Node Knock-out
Network Identification via Node Knock-out
 
Ffst
FfstFfst
Ffst
 
Btp viewmorph
Btp viewmorphBtp viewmorph
Btp viewmorph
 
The Back Propagation Learning Algorithm
The Back Propagation Learning AlgorithmThe Back Propagation Learning Algorithm
The Back Propagation Learning Algorithm
 
call for papers, research paper publishing, where to publish research paper, ...
call for papers, research paper publishing, where to publish research paper, ...call for papers, research paper publishing, where to publish research paper, ...
call for papers, research paper publishing, where to publish research paper, ...
 
Adobe AIR: Stage3D and AGAL
Adobe AIR: Stage3D and AGALAdobe AIR: Stage3D and AGAL
Adobe AIR: Stage3D and AGAL
 
Condition Monitoring Of Unsteadily Operating Equipment
Condition Monitoring Of Unsteadily Operating EquipmentCondition Monitoring Of Unsteadily Operating Equipment
Condition Monitoring Of Unsteadily Operating Equipment
 
Application of differentiation
Application of differentiationApplication of differentiation
Application of differentiation
 
Friedlander et al. Evolution of Bow-Tie Architectures in Biology (2015)
Friedlander et al. Evolution of Bow-Tie Architectures in Biology (2015)Friedlander et al. Evolution of Bow-Tie Architectures in Biology (2015)
Friedlander et al. Evolution of Bow-Tie Architectures in Biology (2015)
 
Cauchy’s Inequality based study of the Differential Equations and the Simple ...
Cauchy’s Inequality based study of the Differential Equations and the Simple ...Cauchy’s Inequality based study of the Differential Equations and the Simple ...
Cauchy’s Inequality based study of the Differential Equations and the Simple ...
 
Finite Difference Method
Finite Difference MethodFinite Difference Method
Finite Difference Method
 
Session02 review-laplace and partial fractionl
Session02 review-laplace and partial fractionlSession02 review-laplace and partial fractionl
Session02 review-laplace and partial fractionl
 
Signal Processing Course : Wavelets
Signal Processing Course : WaveletsSignal Processing Course : Wavelets
Signal Processing Course : Wavelets
 
Fatigue damage - poster
Fatigue damage - posterFatigue damage - poster
Fatigue damage - poster
 
Puzzle-Based Automatic Testing: Bringing Humans Into the Loop by Solving Puzz...
Puzzle-Based Automatic Testing: Bringing Humans Into the Loop by Solving Puzz...Puzzle-Based Automatic Testing: Bringing Humans Into the Loop by Solving Puzz...
Puzzle-Based Automatic Testing: Bringing Humans Into the Loop by Solving Puzz...
 
Integrability and weak diffraction in a two-particle Bose-Hubbard model
 Integrability and weak diffraction in a two-particle Bose-Hubbard model  Integrability and weak diffraction in a two-particle Bose-Hubbard model
Integrability and weak diffraction in a two-particle Bose-Hubbard model
 
Geohydrology ii (3)
Geohydrology ii (3)Geohydrology ii (3)
Geohydrology ii (3)
 

More from ESCOM

redes neuronales Som
redes neuronales Somredes neuronales Som
redes neuronales SomESCOM
 
redes neuronales Som Slides
redes neuronales Som Slidesredes neuronales Som Slides
redes neuronales Som SlidesESCOM
 
red neuronal Som Net
red neuronal Som Netred neuronal Som Net
red neuronal Som NetESCOM
 
redes neuronales Kohonen
redes neuronales Kohonenredes neuronales Kohonen
redes neuronales KohonenESCOM
 
Teoria Resonancia Adaptativa
Teoria Resonancia AdaptativaTeoria Resonancia Adaptativa
Teoria Resonancia AdaptativaESCOM
 
ejemplo red neuronal Art1
ejemplo red neuronal Art1ejemplo red neuronal Art1
ejemplo red neuronal Art1ESCOM
 
redes neuronales tipo Art3
redes neuronales tipo Art3redes neuronales tipo Art3
redes neuronales tipo Art3ESCOM
 
Art2
Art2Art2
Art2ESCOM
 
Redes neuronales tipo Art
Redes neuronales tipo ArtRedes neuronales tipo Art
Redes neuronales tipo ArtESCOM
 
Neocognitron
NeocognitronNeocognitron
NeocognitronESCOM
 
Neocognitron
NeocognitronNeocognitron
NeocognitronESCOM
 
Neocognitron
NeocognitronNeocognitron
NeocognitronESCOM
 
Fukushima Cognitron
Fukushima CognitronFukushima Cognitron
Fukushima CognitronESCOM
 
Counterpropagation NETWORK
Counterpropagation NETWORKCounterpropagation NETWORK
Counterpropagation NETWORKESCOM
 
Counterpropagation NETWORK
Counterpropagation NETWORKCounterpropagation NETWORK
Counterpropagation NETWORKESCOM
 
Counterpropagation
CounterpropagationCounterpropagation
CounterpropagationESCOM
 
Teoría de Resonancia Adaptativa Art2 ARTMAP
Teoría de Resonancia Adaptativa Art2 ARTMAPTeoría de Resonancia Adaptativa Art2 ARTMAP
Teoría de Resonancia Adaptativa Art2 ARTMAPESCOM
 
Teoría de Resonancia Adaptativa ART1
Teoría de Resonancia Adaptativa ART1Teoría de Resonancia Adaptativa ART1
Teoría de Resonancia Adaptativa ART1ESCOM
 
Teoría de Resonancia Adaptativa ART
Teoría de Resonancia Adaptativa ARTTeoría de Resonancia Adaptativa ART
Teoría de Resonancia Adaptativa ARTESCOM
 
learning Vector Quantization LVQ2 LVQ3
learning Vector Quantization LVQ2 LVQ3learning Vector Quantization LVQ2 LVQ3
learning Vector Quantization LVQ2 LVQ3ESCOM
 

More from ESCOM (20)

redes neuronales Som
redes neuronales Somredes neuronales Som
redes neuronales Som
 
redes neuronales Som Slides
redes neuronales Som Slidesredes neuronales Som Slides
redes neuronales Som Slides
 
red neuronal Som Net
red neuronal Som Netred neuronal Som Net
red neuronal Som Net
 
redes neuronales Kohonen
redes neuronales Kohonenredes neuronales Kohonen
redes neuronales Kohonen
 
Teoria Resonancia Adaptativa
Teoria Resonancia AdaptativaTeoria Resonancia Adaptativa
Teoria Resonancia Adaptativa
 
ejemplo red neuronal Art1
ejemplo red neuronal Art1ejemplo red neuronal Art1
ejemplo red neuronal Art1
 
redes neuronales tipo Art3
redes neuronales tipo Art3redes neuronales tipo Art3
redes neuronales tipo Art3
 
Art2
Art2Art2
Art2
 
Redes neuronales tipo Art
Redes neuronales tipo ArtRedes neuronales tipo Art
Redes neuronales tipo Art
 
Neocognitron
NeocognitronNeocognitron
Neocognitron
 
Neocognitron
NeocognitronNeocognitron
Neocognitron
 
Neocognitron
NeocognitronNeocognitron
Neocognitron
 
Fukushima Cognitron
Fukushima CognitronFukushima Cognitron
Fukushima Cognitron
 
Counterpropagation NETWORK
Counterpropagation NETWORKCounterpropagation NETWORK
Counterpropagation NETWORK
 
Counterpropagation NETWORK
Counterpropagation NETWORKCounterpropagation NETWORK
Counterpropagation NETWORK
 
Counterpropagation
CounterpropagationCounterpropagation
Counterpropagation
 
Teoría de Resonancia Adaptativa Art2 ARTMAP
Teoría de Resonancia Adaptativa Art2 ARTMAPTeoría de Resonancia Adaptativa Art2 ARTMAP
Teoría de Resonancia Adaptativa Art2 ARTMAP
 
Teoría de Resonancia Adaptativa ART1
Teoría de Resonancia Adaptativa ART1Teoría de Resonancia Adaptativa ART1
Teoría de Resonancia Adaptativa ART1
 
Teoría de Resonancia Adaptativa ART
Teoría de Resonancia Adaptativa ARTTeoría de Resonancia Adaptativa ART
Teoría de Resonancia Adaptativa ART
 
learning Vector Quantization LVQ2 LVQ3
learning Vector Quantization LVQ2 LVQ3learning Vector Quantization LVQ2 LVQ3
learning Vector Quantization LVQ2 LVQ3
 

Recently uploaded

Textual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSTextual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSMae Pangan
 
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17Celine George
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Mark Reed
 
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...Postal Advocate Inc.
 
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...Nguyen Thanh Tu Collection
 
4.16.24 21st Century Movements for Black Lives.pptx
4.16.24 21st Century Movements for Black Lives.pptx4.16.24 21st Century Movements for Black Lives.pptx
4.16.24 21st Century Movements for Black Lives.pptxmary850239
 
Virtual-Orientation-on-the-Administration-of-NATG12-NATG6-and-ELLNA.pdf
Virtual-Orientation-on-the-Administration-of-NATG12-NATG6-and-ELLNA.pdfVirtual-Orientation-on-the-Administration-of-NATG12-NATG6-and-ELLNA.pdf
Virtual-Orientation-on-the-Administration-of-NATG12-NATG6-and-ELLNA.pdfErwinPantujan2
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfPatidar M
 
ROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptxROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptxVanesaIglesias10
 
4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptxmary850239
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management SystemChristalin Nelson
 
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptxQ4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptxlancelewisportillo
 
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)lakshayb543
 
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxINTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxHumphrey A Beña
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Celine George
 
Integumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.pptIntegumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.pptshraddhaparab530
 
Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4JOYLYNSAMANIEGO
 
Oppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and FilmOppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and FilmStan Meyer
 

Recently uploaded (20)

Paradigm shift in nursing research by RS MEHTA
Paradigm shift in nursing research by RS MEHTAParadigm shift in nursing research by RS MEHTA
Paradigm shift in nursing research by RS MEHTA
 
Textual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHSTextual Evidence in Reading and Writing of SHS
Textual Evidence in Reading and Writing of SHS
 
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
Incoming and Outgoing Shipments in 3 STEPS Using Odoo 17
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)
 
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
USPS® Forced Meter Migration - How to Know if Your Postage Meter Will Soon be...
 
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
 
4.16.24 21st Century Movements for Black Lives.pptx
4.16.24 21st Century Movements for Black Lives.pptx4.16.24 21st Century Movements for Black Lives.pptx
4.16.24 21st Century Movements for Black Lives.pptx
 
Virtual-Orientation-on-the-Administration-of-NATG12-NATG6-and-ELLNA.pdf
Virtual-Orientation-on-the-Administration-of-NATG12-NATG6-and-ELLNA.pdfVirtual-Orientation-on-the-Administration-of-NATG12-NATG6-and-ELLNA.pdf
Virtual-Orientation-on-the-Administration-of-NATG12-NATG6-and-ELLNA.pdf
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdf
 
ROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptxROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptx
 
4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management System
 
FINALS_OF_LEFT_ON_C'N_EL_DORADO_2024.pptx
FINALS_OF_LEFT_ON_C'N_EL_DORADO_2024.pptxFINALS_OF_LEFT_ON_C'N_EL_DORADO_2024.pptx
FINALS_OF_LEFT_ON_C'N_EL_DORADO_2024.pptx
 
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptxQ4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
 
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
 
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxINTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17
 
Integumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.pptIntegumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.ppt
 
Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4
 
Oppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and FilmOppenheimer Film Discussion for Philosophy and Film
Oppenheimer Film Discussion for Philosophy and Film
 

Self Organinising neural networks

  • 1. Self Organising Neural Networks Kohonen Networks. A Problem with Neural Networks. ART. Beal, R. and Jackson, T. (1990). Neural Computing: An Introduction. Chapters 5 & 7. Adam Hilger, NY. Hertz, J., Krogh, A. and Palmer, R. (1991). Introduction to the Theory of Neural Computation. Chapter 9. Addison–Wesley. NY. Grossberg, S. (1987). Competitive Learning: from interactive acti- vation to adaptive resonance. Cognitive Science, 11: 23–63. 1
  • 2. Kohonen Self Organising Networks Kohonen, T. (1982). Self–organized formation of topologically cor- rect feature maps., Biological Cybernetics, 43: 59–69. An abstraction from earlier models (e.g. Malsburg, 1973). The formation of feature maps (introducing a geo- metric layout). Popular and useful. Can be traced to biologically inspired origins. Why have topographic mappings? – Minimal wiring – Help subsequent processing layers. Example: Xenopus retinotectal mapping (Price & Will- shaw 2000, p121). 2
  • 3. Basic Kohonen Network Geometric arrangement of units. Units respond to “part” of the environment. Neighbouring units should respond to similar parts of the environment. Winning unit selected by: Ü Û min Ü Û where Û is the weight vector of winning unit, and Ü is the input pattern. and Neighbourhoods... 3
  • 4. Neighbourhoods in the Kohonen Network Example in 2D. Neighbourhood of winning unit called Æ . 4
  • 5. Learning in the Kohonen Network All units in Æ are updated. dÛ ´ µ ´ µ   Û ´Øµ « Ø Ü Ø for ¾ Æ dØ ¼ otherwise where dÛ dØ = change in weight over time. ´µ « Ø = time dependent learning parameter. Ü ´Øµ = input component at time Ø. Û ´Øµ = weight from input to unit at time Ø. ¯ Geometrical effect: move weight vector closer to in- put vector. ¯ « is strongest for winner and can decrease with dis- tance. Also decreases over time for stability. 5
  • 6. Biological origins of the Neighbourhoods Lateral interaction of the units. Mexican Hat form: 1.6 1.4 1.2 1 0.8 0.6 0.4 0.2 0 -0.2 -0.4 -100 -80 -60 -40 -20 0 20 40 60 80 100 3 2 1 0 -1 40 30 40 20 30 20 10 10 0 0 6
  • 7. Biological origins of the Neighbourhoods: Mals- burg Excitatory connections: Excitatory units Inhibitory units Inhibitory connections: Excitatory units Inhibitory units Implements winner-take-all processing. 7
  • 8. 1-d example 4 3 2 1 5 4 3 2 1 5 4 3 2 5 1 5 4 3 2 1 5 4 3 2 1 8
  • 9. 2-d example: uniform density 8x8 units in 2D lattice 2 input lines. Inputs between ·½ and  ½. Input space: +1 -1 +1 -1 9
  • 10. 2-d example: uniform density 10
  • 11. 2-d example: non-uniform density Same 8x8 units in 2D lattice. Same input space. Different input distribution +1 -1 +1 -1 11
  • 13. 2-d µ 1-d example: dimension reduction 2-d input uniform density; 1-d output arrangement. “Space-filling” (Peano) curves; can solve Travelling Salesman Problem. init wts epoch 10 epoch 500 epoch 700 13
  • 14. Example Application of Kohonen’s Network The Phonetic Typewriter MP Filter A/D FFT Rules Kohonen Network Problem: Classification of phonemes in real time. Pre and post processing. Network trained on time sliced speech wave forms. Rules needed to handle co-articulation effects. 14
  • 15. A Problem with Neural Networks Consider 3 network examples: Kohonen Network. Associative Network. Feed Forward Back-propagation. Under the situation: Network learns environment (or I/O relations). Network is stable in the environment. Network is placed in a new environment. What happens: Kohonen Network won’t learn. Associative Network OK. Feed Forward Back-propagation Forgets. called The Stability/Plasticity Dilemma. 15
  • 16. Adaptive Resonance Theory Grossberg, S. (1976a). Adaptive pattern classification and univer- sal recoding I: Feedback, expectation, olfaction, illusions. Biological Cybernetics, 23: 187–202. a “neural network that self–organize[s] stable pat- tern recognition codes in real time, in response to arbitrary sequences of input patterns”. ART1 (1976). Localist representation, binary patterns. ART2 (1987). Localist representation, analog patterns. ART3 (1990). Distributed representation, analog pat- terns. Desirable properties: plastic + stable biological mechanisms analytical math foundation 16
  • 17. ART1 Attentional subsystem F2 units ( ) Orienting subsystem + (Ø ) +( ) - + F1 units (Ü ) - r G + + + Input (Ü ) F1  F2 fully connected, excitatory ( ). F2  F1 fully connected, excitatory (Ø ). Pattern of activation on F1 and F2 called Short Term Memory. Weight representations called Long Term Memory. Localist representations of binary input patterns. 17
  • 18. Summary of ART 1 (Lippmann, 1987). N = number of F1 units. Step 1: Initialization Ø ½ ½ ½·Æ Set vigilance parameter ¼ ½ Step 2: apply new input (binary Ü ) Step 3: compute F2 activation Æ Ü ½ Step 4: find best matching node , where . Step 5: vigilance test Æ Æ Ü Ì ¡ Ø Ü ½ ½ Ì ¡ Is If no, go to step 6. If yes go to step 7. Step 6: mismatch/reset: set ¼ and go to step 4. Step 7: resonance — adapt best match Ø Ø Ü Ø · È Æ ½Ø Ü Step 8: Re-enable all F2 units and go to step 2 18
  • 19. ART1: Example INPUT F2 UNITS REPRESENT: UNIT 1 UNIT 2 UNIT 3 UNIT 4 UNIT 5 resonance resonance 1st choice resonance reset 2nd choice 1st choice resonance reset reset 3rd choice 1st choice 2nd choice resonance reset reset reset 1st choice resonance 1st choice 2nd choice reset resonance 1st choice 4th choice 3rd choice 2nd choice resonance reset reset reset reset 19
  • 20. Summary Simple? Interesting biological parallels. Diverse applications. Extensions. 20