SlideShare une entreprise Scribd logo
1  sur  22
Télécharger pour lire hors ligne
An incremental network for on-line
 unsupervised classification and
        topology learning

      Shen Furao       Osamu Hasegawa


Neural Networks, Vol.19, No.1, pp.90-106, (2006)
Background: Objective of unsupervised learning (1)
    Clustering: Construct decision boundaries
      based on unlabeled data.
      – Single-link, complete-link, CURE
         • Computation overload
         • Much memory space
         • Unsuitable for large data sets or online data
      – K-means:
         •   Dependence on initial starting conditions
         •   Tendency to result in local minima
         •   Determine the number of clusters k in advance
         •   data sets consisting only of isotropic clusters
Background: Objective of unsupervised learning (2)
Topology learning: Given some high-dimensional data
  distribution, find a topological structure that closely
  reflects the topology of the data distribution
   – SOM: self-organizing map
       • predetermined structure and size
       • posterior choice of class labels for the prototypes
   – CHL+NG: competitive Hebbian learning + neural gas
       • a priori decision about the network size
       • ranking of all nodes in each adaptation step
       • use of adaptation parameter
   – GNG: growing neural gas
       • permanent increase in the number of nodes
       • permanent drift of centers to capture input probability
         density
Background: Online or life-long learning
Fundamental issue (Stability-Plasticity Dilemma): How can
  a learning system adapt to new information without
  corrupting or forgetting previously learned information
   – GNG-U: deletes nodes which are located in regions of
     a low input probability density
      • learned old prototype patterns will be destroyed
   – Hybrid network: Fuzzy ARTMAP + PNN
   – Life-long learning with improved GNG: learn number
     of nodes needed for current task
      • only for supervised life-long learning
Objectives of proposed algorithm
• To process the on-line non-stationary data.
• To do the unsupervised learning without any priori
  condition such as:
   • suitable number of nodes
   • a good initial codebook
   • how many classes there are
• Report a suitable number of classes
• Represent the topological structure of the input
  probability density.
• Separate the classes with some low-density overlaps
• Detect the main structure of clusters polluted by noises.
Proposed algorithm

          First Layer            Second Layer
Input      Growing       First     Growing        Second
pattern    Network      Output     Network        Output




          Insert        Delete
                                       Classify
          Node          Node
Algorithms
• Insert new nodes
  – Criterion: nodes with high errors serve as a criterion
    to insert a new node
  – error-radius is used to judge if the insert is successful
• Delete nodes
  – Criterion: remove nodes in low probability density
    regions
  – Realize: delete nodes with no or only one direct
    topology neighbor
• Classify
  – Criterion: all nodes linked with edges will be one
    cluster
Experiment
• Stationary environment: patterns are randomly chosen
  from all area A, B, C, D and E
• NON-Stationary environment:
                                       Environment
                                 I II III IV V VI VII
                            A 1 0 1 0 0 0 0
                             B 0 1 0 1 0 0 0
                             C 0 0 1 0 0 1 0
                            D 0 0 0 1 1 0 0
                            E1 0 0 0 0 1 0 0
                            E2 0 0 0 0 0 1 0
   Original Data Set        E3 0 0 0 0 0 0 1
Experiment: Stationary environment




Original Data Set   Traditional method: GNG
Experiment: Stationary environment




Proposed method: first layer   Proposed method: final results
Experiment: Non-stationary environment




  GNG result              GNG-U result
Experiment: Non-stationary environment




         Proposed method: first layer
Experiment: Non-stationary environment




         Proposed method: first layer
Experiment: Non-stationary environment




Proposed method: first layer Proposed method: Final output
Experiment: Non-stationary environment




Number of growing nodes during online learning
     (Environment 1 ~ Environment 7)
Experiment: Real World Data
(ATT_FACE)
Facial Image




               (a) 10 classes




               (b) 10 samples of class 1
Experiment:Vector




           Vector of (a)




           Vector of (b)
Experiment: Face Recognition results
                             10 clusters

                             Stationary
                             Correct
                             Recognition
                             Ratio: 90%

                             Non-Stationary
                             Correct
                             Recognition
                             Ratio: 86%
Experiment: Vector Quantization




                             Stationary Environment: Decoding
 Original Lena (512*512*8)
                             image, 130 nodes, 0.45bpp,
                             PSNR = 30.79dB
Experiment: Compare with GNG
   Stationary Environment

                      Number
                                  bpp    PSNR
                      of Nodes
      First-layer           130   0.45   30.79

         GNG                130   0.45   29.98

     Second-layer           52    0.34   29.29

         GNG                52    0.34   28.61
Experiment: Non-stationary Environment




First-layer: 499 nodes, 0.56bpp,   Second-layer: 64 nodes, 0.375bpp,
PSNR = 32.91dB                     PSNR = 29.66dB
Conclusion
• An autonomous learning system for
  unsupervised classification and topology
  representation task
• Grow incrementally and learn the number of
  nodes needed to solve current task
• Accommodate input patterns of on-line non-
  stationary data distribution
• Eliminate noise in the input data

Contenu connexe

Tendances

Lecun 20060816-ciar-02-deep learning for generic object recognition
Lecun 20060816-ciar-02-deep learning for generic object recognitionLecun 20060816-ciar-02-deep learning for generic object recognition
Lecun 20060816-ciar-02-deep learning for generic object recognition
zukun
 

Tendances (20)

Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...
Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...
Lecture 02: Machine Learning for Language Technology - Decision Trees and Nea...
 
#6 PyData Warsaw: Deep learning for image segmentation
#6 PyData Warsaw: Deep learning for image segmentation#6 PyData Warsaw: Deep learning for image segmentation
#6 PyData Warsaw: Deep learning for image segmentation
 
Deep Learning and TensorFlow
Deep Learning and TensorFlowDeep Learning and TensorFlow
Deep Learning and TensorFlow
 
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
 
Score based Generative Modeling through Stochastic Differential Equations
Score based Generative Modeling through Stochastic Differential EquationsScore based Generative Modeling through Stochastic Differential Equations
Score based Generative Modeling through Stochastic Differential Equations
 
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
 
Deep learning lecture - part 1 (basics, CNN)
Deep learning lecture - part 1 (basics, CNN)Deep learning lecture - part 1 (basics, CNN)
Deep learning lecture - part 1 (basics, CNN)
 
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
 
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
 
Batch normalization paper review
Batch normalization paper reviewBatch normalization paper review
Batch normalization paper review
 
CVPR2008 tutorial generalized pca
CVPR2008 tutorial generalized pcaCVPR2008 tutorial generalized pca
CVPR2008 tutorial generalized pca
 
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
 
Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
Skip RNN: Learning to Skip State Updates in Recurrent Neural NetworksSkip RNN: Learning to Skip State Updates in Recurrent Neural Networks
Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
 
EMNLP 2014: Opinion Mining with Deep Recurrent Neural Network
EMNLP 2014: Opinion Mining with Deep Recurrent Neural NetworkEMNLP 2014: Opinion Mining with Deep Recurrent Neural Network
EMNLP 2014: Opinion Mining with Deep Recurrent Neural Network
 
Lecun 20060816-ciar-02-deep learning for generic object recognition
Lecun 20060816-ciar-02-deep learning for generic object recognitionLecun 20060816-ciar-02-deep learning for generic object recognition
Lecun 20060816-ciar-02-deep learning for generic object recognition
 
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
 
Yolo releases gianmaria
Yolo releases gianmariaYolo releases gianmaria
Yolo releases gianmaria
 
The Perceptron - Xavier Giro-i-Nieto - UPC Barcelona 2018
The Perceptron - Xavier Giro-i-Nieto - UPC Barcelona 2018The Perceptron - Xavier Giro-i-Nieto - UPC Barcelona 2018
The Perceptron - Xavier Giro-i-Nieto - UPC Barcelona 2018
 
Backpropagation - Elisa Sayrol - UPC Barcelona 2018
Backpropagation - Elisa Sayrol - UPC Barcelona 2018Backpropagation - Elisa Sayrol - UPC Barcelona 2018
Backpropagation - Elisa Sayrol - UPC Barcelona 2018
 
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
 

En vedette

Supervised Classification
Supervised ClassificationSupervised Classification
Supervised Classification
Chad Yowler
 
Program Evaluation and Review Technique (PERT)
Program Evaluation and Review Technique (PERT)Program Evaluation and Review Technique (PERT)
Program Evaluation and Review Technique (PERT)
Abhishek Pachisia
 
Pert & cpm project management
Pert & cpm   project managementPert & cpm   project management
Pert & cpm project management
Rahul Dubey
 

En vedette (12)

Band Combination of Landsat 8 Earth-observing Satellite Images
Band Combination of Landsat 8 Earth-observing Satellite ImagesBand Combination of Landsat 8 Earth-observing Satellite Images
Band Combination of Landsat 8 Earth-observing Satellite Images
 
Normalized Difference Vegetation Index (NDVI)
Normalized Difference Vegetation Index (NDVI)Normalized Difference Vegetation Index (NDVI)
Normalized Difference Vegetation Index (NDVI)
 
NDVI
NDVINDVI
NDVI
 
Few Indicies(NDVI... etc) performed on ERDAS software using Model Maker
Few Indicies(NDVI... etc) performed on ERDAS software using Model MakerFew Indicies(NDVI... etc) performed on ERDAS software using Model Maker
Few Indicies(NDVI... etc) performed on ERDAS software using Model Maker
 
Land cover supervised classification at Toro Park, California
Land cover supervised classification at Toro Park, CaliforniaLand cover supervised classification at Toro Park, California
Land cover supervised classification at Toro Park, California
 
Clustering
ClusteringClustering
Clustering
 
Supervised Classification
Supervised ClassificationSupervised Classification
Supervised Classification
 
Presentacion elafis Brasil 2009
Presentacion elafis Brasil 2009Presentacion elafis Brasil 2009
Presentacion elafis Brasil 2009
 
Introduce variable/ Indices using landsat image
Introduce variable/ Indices using landsat imageIntroduce variable/ Indices using landsat image
Introduce variable/ Indices using landsat image
 
Pert & Cpm
Pert & CpmPert & Cpm
Pert & Cpm
 
Program Evaluation and Review Technique (PERT)
Program Evaluation and Review Technique (PERT)Program Evaluation and Review Technique (PERT)
Program Evaluation and Review Technique (PERT)
 
Pert & cpm project management
Pert & cpm   project managementPert & cpm   project management
Pert & cpm project management
 

Similaire à Original SOINN

Similaire à Original SOINN (20)

Deep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr SanparitDeep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr Sanparit
 
You only look once (YOLO) : unified real time object detection
You only look once (YOLO) : unified real time object detectionYou only look once (YOLO) : unified real time object detection
You only look once (YOLO) : unified real time object detection
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
Wits presentation 6_28072015
Wits presentation 6_28072015Wits presentation 6_28072015
Wits presentation 6_28072015
 
Paper review
Paper reviewPaper review
Paper review
 
Fundamental of deep learning
Fundamental of deep learningFundamental of deep learning
Fundamental of deep learning
 
NS-CUK Seminar: S.T.Nguyen, Review on "Graph Pointer Neural Networks", AAAI 2022
NS-CUK Seminar: S.T.Nguyen, Review on "Graph Pointer Neural Networks", AAAI 2022NS-CUK Seminar: S.T.Nguyen, Review on "Graph Pointer Neural Networks", AAAI 2022
NS-CUK Seminar: S.T.Nguyen, Review on "Graph Pointer Neural Networks", AAAI 2022
 
Deep learning with TensorFlow
Deep learning with TensorFlowDeep learning with TensorFlow
Deep learning with TensorFlow
 
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
 
Deep learning based object detection basics
Deep learning based object detection basicsDeep learning based object detection basics
Deep learning based object detection basics
 
Anomaly detection using deep one class classifier
Anomaly detection using deep one class classifierAnomaly detection using deep one class classifier
Anomaly detection using deep one class classifier
 
Deep learning
Deep learningDeep learning
Deep learning
 
Audio tagging system using densely connected convolutional networks (DCASE201...
Audio tagging system using densely connected convolutional networks (DCASE201...Audio tagging system using densely connected convolutional networks (DCASE201...
Audio tagging system using densely connected convolutional networks (DCASE201...
 
Neural netorksmatching
Neural netorksmatchingNeural netorksmatching
Neural netorksmatching
 
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesAI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
 
object detection paper review
object detection paper reviewobject detection paper review
object detection paper review
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
 
Introducción a las redes convolucionales
Introducción a las redes convolucionalesIntroducción a las redes convolucionales
Introducción a las redes convolucionales
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
 
Exploring Randomly Wired Neural Networks for Image Recognition
Exploring Randomly Wired Neural Networks for Image RecognitionExploring Randomly Wired Neural Networks for Image Recognition
Exploring Randomly Wired Neural Networks for Image Recognition
 

Plus de SOINN Inc.

Dr.Kawewong Ph.D Thesis
Dr.Kawewong Ph.D ThesisDr.Kawewong Ph.D Thesis
Dr.Kawewong Ph.D Thesis
SOINN Inc.
 
ロボットによる一般問題解決
ロボットによる一般問題解決ロボットによる一般問題解決
ロボットによる一般問題解決
SOINN Inc.
 
SOIAM (SOINN-AM)
SOIAM (SOINN-AM)SOIAM (SOINN-AM)
SOIAM (SOINN-AM)
SOINN Inc.
 
学生さんへのメッセージ
学生さんへのメッセージ学生さんへのメッセージ
学生さんへのメッセージ
SOINN Inc.
 
超高速オンライン転移学習
超高速オンライン転移学習超高速オンライン転移学習
超高速オンライン転移学習
SOINN Inc.
 
東工大長谷川修研紹介 2011 (8月1日版)
東工大長谷川修研紹介 2011 (8月1日版)東工大長谷川修研紹介 2011 (8月1日版)
東工大長谷川修研紹介 2011 (8月1日版)
SOINN Inc.
 
東工大 長谷川修研の環境学習・認識・探索技術
東工大 長谷川修研の環境学習・認識・探索技術東工大 長谷川修研の環境学習・認識・探索技術
東工大 長谷川修研の環境学習・認識・探索技術
SOINN Inc.
 

Plus de SOINN Inc. (14)

PBAI
PBAIPBAI
PBAI
 
Dr.Kawewong Ph.D Thesis
Dr.Kawewong Ph.D ThesisDr.Kawewong Ph.D Thesis
Dr.Kawewong Ph.D Thesis
 
I
II
I
 
PIRF-NAV2
PIRF-NAV2PIRF-NAV2
PIRF-NAV2
 
SSA-SOINN
SSA-SOINNSSA-SOINN
SSA-SOINN
 
E-SOINN
E-SOINNE-SOINN
E-SOINN
 
ロボットによる一般問題解決
ロボットによる一般問題解決ロボットによる一般問題解決
ロボットによる一般問題解決
 
SOINN PBR
SOINN PBRSOINN PBR
SOINN PBR
 
SOIAM (SOINN-AM)
SOIAM (SOINN-AM)SOIAM (SOINN-AM)
SOIAM (SOINN-AM)
 
SOINN-AM
SOINN-AMSOINN-AM
SOINN-AM
 
学生さんへのメッセージ
学生さんへのメッセージ学生さんへのメッセージ
学生さんへのメッセージ
 
超高速オンライン転移学習
超高速オンライン転移学習超高速オンライン転移学習
超高速オンライン転移学習
 
東工大長谷川修研紹介 2011 (8月1日版)
東工大長谷川修研紹介 2011 (8月1日版)東工大長谷川修研紹介 2011 (8月1日版)
東工大長谷川修研紹介 2011 (8月1日版)
 
東工大 長谷川修研の環境学習・認識・探索技術
東工大 長谷川修研の環境学習・認識・探索技術東工大 長谷川修研の環境学習・認識・探索技術
東工大 長谷川修研の環境学習・認識・探索技術
 

Dernier

Dernier (20)

Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 

Original SOINN

  • 1. An incremental network for on-line unsupervised classification and topology learning Shen Furao Osamu Hasegawa Neural Networks, Vol.19, No.1, pp.90-106, (2006)
  • 2. Background: Objective of unsupervised learning (1) Clustering: Construct decision boundaries based on unlabeled data. – Single-link, complete-link, CURE • Computation overload • Much memory space • Unsuitable for large data sets or online data – K-means: • Dependence on initial starting conditions • Tendency to result in local minima • Determine the number of clusters k in advance • data sets consisting only of isotropic clusters
  • 3. Background: Objective of unsupervised learning (2) Topology learning: Given some high-dimensional data distribution, find a topological structure that closely reflects the topology of the data distribution – SOM: self-organizing map • predetermined structure and size • posterior choice of class labels for the prototypes – CHL+NG: competitive Hebbian learning + neural gas • a priori decision about the network size • ranking of all nodes in each adaptation step • use of adaptation parameter – GNG: growing neural gas • permanent increase in the number of nodes • permanent drift of centers to capture input probability density
  • 4. Background: Online or life-long learning Fundamental issue (Stability-Plasticity Dilemma): How can a learning system adapt to new information without corrupting or forgetting previously learned information – GNG-U: deletes nodes which are located in regions of a low input probability density • learned old prototype patterns will be destroyed – Hybrid network: Fuzzy ARTMAP + PNN – Life-long learning with improved GNG: learn number of nodes needed for current task • only for supervised life-long learning
  • 5. Objectives of proposed algorithm • To process the on-line non-stationary data. • To do the unsupervised learning without any priori condition such as: • suitable number of nodes • a good initial codebook • how many classes there are • Report a suitable number of classes • Represent the topological structure of the input probability density. • Separate the classes with some low-density overlaps • Detect the main structure of clusters polluted by noises.
  • 6. Proposed algorithm First Layer Second Layer Input Growing First Growing Second pattern Network Output Network Output Insert Delete Classify Node Node
  • 7. Algorithms • Insert new nodes – Criterion: nodes with high errors serve as a criterion to insert a new node – error-radius is used to judge if the insert is successful • Delete nodes – Criterion: remove nodes in low probability density regions – Realize: delete nodes with no or only one direct topology neighbor • Classify – Criterion: all nodes linked with edges will be one cluster
  • 8. Experiment • Stationary environment: patterns are randomly chosen from all area A, B, C, D and E • NON-Stationary environment: Environment I II III IV V VI VII A 1 0 1 0 0 0 0 B 0 1 0 1 0 0 0 C 0 0 1 0 0 1 0 D 0 0 0 1 1 0 0 E1 0 0 0 0 1 0 0 E2 0 0 0 0 0 1 0 Original Data Set E3 0 0 0 0 0 0 1
  • 9. Experiment: Stationary environment Original Data Set Traditional method: GNG
  • 10. Experiment: Stationary environment Proposed method: first layer Proposed method: final results
  • 11. Experiment: Non-stationary environment GNG result GNG-U result
  • 12. Experiment: Non-stationary environment Proposed method: first layer
  • 13. Experiment: Non-stationary environment Proposed method: first layer
  • 14. Experiment: Non-stationary environment Proposed method: first layer Proposed method: Final output
  • 15. Experiment: Non-stationary environment Number of growing nodes during online learning (Environment 1 ~ Environment 7)
  • 16. Experiment: Real World Data (ATT_FACE) Facial Image (a) 10 classes (b) 10 samples of class 1
  • 17. Experiment:Vector Vector of (a) Vector of (b)
  • 18. Experiment: Face Recognition results 10 clusters Stationary Correct Recognition Ratio: 90% Non-Stationary Correct Recognition Ratio: 86%
  • 19. Experiment: Vector Quantization Stationary Environment: Decoding Original Lena (512*512*8) image, 130 nodes, 0.45bpp, PSNR = 30.79dB
  • 20. Experiment: Compare with GNG Stationary Environment Number bpp PSNR of Nodes First-layer 130 0.45 30.79 GNG 130 0.45 29.98 Second-layer 52 0.34 29.29 GNG 52 0.34 28.61
  • 21. Experiment: Non-stationary Environment First-layer: 499 nodes, 0.56bpp, Second-layer: 64 nodes, 0.375bpp, PSNR = 32.91dB PSNR = 29.66dB
  • 22. Conclusion • An autonomous learning system for unsupervised classification and topology representation task • Grow incrementally and learn the number of nodes needed to solve current task • Accommodate input patterns of on-line non- stationary data distribution • Eliminate noise in the input data