the information bottleneck method
play

The Information Bottleneck Method Naftali Tishby, Fernando C. - PowerPoint PPT Presentation

The Information Bottleneck Method Naftali Tishby, Fernando C. Pereira, William Bialek Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method Naftali Tishby, Fernando C. Pereira, William Bialek The Information


  1. The Information Bottleneck Method Naftali Tishby, Fernando C. Pereira, William Bialek Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  2. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  3. What is information bottleneck? It is a technique for finding the best tradeoff between accuracy and complexity. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  4. Example Speech compression: A transcript of spoken words has low entropy = ⇒ It can be compressed without loosing the information about the words. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  5. Problem Definition Input signals x ∈ X , and y ∈ Y mapping function f: X → Y P ( X = x ) , P ( Y = y , X = x ) Output X → ˜ X ˜ X → Y Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  6. Example 1 X = Speech signal Y = Transcription signal 2 X = Speech signal Y = Speakers identity Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  7. Relevant quantization Mapping X → ˜ X � Soft Partitioning P (˜ x | x ) ← − Hard Partitioning P (˜ x ) = � x p ( x ) p (˜ x | x ) Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  8. What is a good quantization? The first factor is the rate, or the average number of bits per message needed to specify an element in the codebook without confusion. This number per element of X is bounded from below by the mutual information Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  9. H ( X ) , I ( X , ˜ X ) , H ( X | ˜ X ) Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  10. The average volume of the elements of X that are mapped to the same codeword is 2 H ( X | ˜ X ) Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  11. Information rate alone is not enough to characterize good quantization since the rate can always be reduced by throwing away details of the original signal x. We need therefore some additional constraints. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  12. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  13. The information bottleneck Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  14. The optimal assignment, that minimizes previous equation, satisfies the equation p ( y | ˜ x ) can be computed by Bayes’ rule and Markov chain condition ˜ X ← X ← Y Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  15. The information bottleneck iterative algorithm Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  16. The structure of the solutions The formal solution of the self consistent equations, described above, still requires a specification of the structure and cardinality of ˜ X , as in rate distortion theory. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  17. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  18. a novel implementation of the information bottleneck method for unsupervised document clustering. Input: X = Documents, Y = Words P ( X ) and P ( X , Y ) Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  19. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  20. Hard Clustering β − → ∞ Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  21. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  22. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  23. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  24. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  25. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  26. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  27. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

  28. Naftali Tishby, Fernando C. Pereira, William Bialek The Information Bottleneck Method

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend