1 / 34

Tabu Search for Codebook Design

Tabu Search for Codebook Design. An evolution-based tabu search approach to codebook design Pattern Recognition, 2006 Shih-Ming Pan, Kuo-Sheng Cheng. Glover(1986) 1. Proposed the tabu search to solve the combinational optimization. 2. Use tabu memory to record the previously

emery
Download Presentation

Tabu Search for Codebook Design

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. Tabu Search for Codebook Design An evolution-based tabu search approach to codebook design Pattern Recognition, 2006 Shih-Ming Pan, Kuo-Sheng Cheng

  2. Glover(1986) 1. Proposed the tabu search to solve the combinational optimization. 2. Use tabu memory to record the previously search result. Six steps of tabu search • Initialization • A set of moves (neighboring solution) • A memory of a certain size • Tabu restriction rule • A set of aspiration rule • Stop criterion Tabu memory

  3. Codebook generation (Franti, pattern recognition, 1998) • Initial solution: K-mean algorithm • Neighboring solution: use swap the closest training vector to replace the codeword of cluster • Tabu memory is determined empirically • Tabu restriction is defined by “oldest solution is removed. • No aspiration rule. • Stopping criterion, N iteration • Disadvantage: Single initial solution

  4. Generating Parent Population Pp Best solution population Ibest Tabu memory asexual reproduction Sexual reproduction update Par Offspring generation I’ Psr I’’ Ioi

  5. Normal Defective Ibest Number = 2p Tabu distance Evolution/ Degeneration Number = p Ioi Compute Tabu Distance Compute Distortion competition Fitness Evaluation foi

  6. Evolution-based tabu search

  7. competition

  8. Evolution-based tabu search

More Related