1 / 21

Outlines

Self-organizing maps whose topologies can be learned with adaptive binary search trees using conditional rotations. Presenter : Bei -YI Jiang Authors : César A. Astudillo , B. John Oommen 2014. Pattern Recognition. Outlines. Motivation Objectives Methodology Experiments Conclusions

kerryn
Download Presentation

Outlines

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Self-organizing maps whose topologies can be learned with adaptive binary search trees using conditional rotations Presenter : Bei-YI JiangAuthors : César A. Astudillo, B. John Oommen2014. Pattern Recognition

  2. Outlines • Motivation • Objectives • Methodology • Experiments • Conclusions • Comments

  3. Motivation • The user must specify the lattice a priori, which has the effect that he must run the ANN a number of times to obtain a suitable configuration. • The size of the maps, where a lesser number of neurons often represent the data inaccurately.

  4. Objectives • The user need not be aware of any of the topological peculiaritiesof the stochastic data distribution. • The state-of-the-art approaches attempt to render the topology more flexible, so as to represent complicated data distributions in a better way and/or to make the process faster by, for instance, speeding up the task of determining the BMU.

  5. Methodology

  6. Methodology

  7. Methodology

  8. Methodology

  9. Methodology

  10. Methodology

  11. Methodology

  12. Methodology

  13. Experiments

  14. Experiments

  15. Experiments

  16. Experiments

  17. Experiments

  18. Experiments

  19. Experiments

  20. Conclusions • The user need not be aware of any of the topological peculiarities of the stochastic data distribution. • It can represent the underlying data distribution and its structure in a more accurate manner.

  21. Comments • Advantages • user does not need to have a priori knowledge • Preserve the topological properties • Applications • Adaptive data structures • Self organizing maps

More Related