1 / 52

Adapting Representation in Genetic Programming

Adapting Representation in Genetic Programming. Cezary Z. Janikow UMSL. Work partly done at NASA/JSC. Roadmap. Search Space and Redundant Representations Constrained GP CGP Technology Adaptable CGP ACGP ACGP1.1.1 methodology Some results ACGP2.1 ( NEW ), future.

primo
Download Presentation

Adapting Representation in Genetic Programming

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. Adapting Representation in Genetic Programming Cezary Z. Janikow UMSL Work partly done at NASA/JSC

  2. Roadmap • Search Space and Redundant Representations • Constrained GP CGP • Technology • Adaptable CGP ACGP • ACGP1.1.1 methodology • Some results • ACGP2.1 (NEW), future

  3. GP Search Space • Best mappings • One-to-one • Onto • Real life • Redundant • Many-to-one • Work done on redundant space in GA supports • Overrepresentation of the best solutions • “Closeness” of genotype and phenotype

  4. GP Search Space 2-dim space • Tree structures • constrained by size limits and function arity • Tree instances of specific structures • constrained by domain sizes

  5. Real Life Mappings • Allow all (help by closure) • Strong pruning • Explicit • Structure-preserving cross, STGP, CGP, CFG-GP • Weak (probabilistic) pruning • Implicit: • Evolution itself • Penalty (explicit on phenotype) • Explicit • Non-uniform mutation/cross: CGP, ACGP

  6. + 2 + y 4 / + 2 / x sin + + + 2 2 a x sin y 4 a GP Crossover – strong vs. weak pruning (non-uniform)

  7. / + 2 x sin a GP Mutation – strong vs. weak pruning / + 2 x * c 3

  8. Unpruned uniform distribution Mutation/Crossover Pi Pi+1 Reproduction GP at work

  9. Typed GP at work Pruned uniform distribution Mutation/Crossover Pi Pi+1 Reproduction CFG-based, STGP, -GP,CGP, Structure-Preserving Crossover

  10. CGP: explicit strong and explicit weak pruning Pruned non-uniform distribution CSL Mutation/Crossover Pi Pi+1 Reproduction

  11. ACGP: strong and weak pruning, adaptable Pruned non-uniform distribution CSL Mutation/Crossover Pi Pi+1 Reproduction

  12. CGPConstrained Genetic Programming Principles Technology Examples

  13. Why CGP? • Existing technology for ACGP as is • Efficient existing technology allowing input and processing of strong constraints and weak heuristics • Implemented into lil-gp • But no need to couple

  14. CGP Principles Constraining GP to search only within desired space • Constraining options • Strong FT constraints • Strong Data typing • Weak Heuristics • probabilistic (think of shades) pruning

  15. CGP Current Capabilities Local heuristics and constraints • On specific labels • On data types • Overloaded (polymorphic) functions • Weighted heuristics

  16. ACGP - Adaptable CGP Application context Principles ACGP at work Example of Heuristics Results V1.1.1 vs. near-future v2.1 vs. far-future

  17. ACGP Application Context • Learn heuristics off-line to • Knowledge discovery • Solve better next time • Solve harder problem next time • Create a library of heuristics • Most results shown here • Learn heuristics on-line during problem solving • hBOA • Some results here

  18. ACGP Principles • Adjust the heuristics changing the probability distribution • Measure utility in mutation/crossover • Immediate impact but • Bucket Brigade problem in mutation • modest improvements • Observe applications to surviving chromosomes • Co-evolution • Solutions vs. library of heuristics • Observe distribution of local heuristics • current ACGP, reported here, better improvements

  19. ACGP Meta-Loop

  20. ACGP Iterations

  21. CGP1.1 and ACGP1.1.1 Heursitics • Current node info retained in CGP1.1 tree • Current heuristics in ACGP1.1.1 • Updates heuristics at different schedules • Uses info on expressed genes • Could go to deeper heuristics

  22. ACGP Experiment Domain 11-Multiplexer • 3 addresses • 8 data bits • pass through one data bit • GP settings • functions: if/else, and, or, not • terminals: addresses and data

  23. Previously Identified Heuristics • DNF or sufficient set (e.g., {and, not}) • No • if only is best • if-arg1 {addresses,not} • if-arg2/3 {if,data} • Yes • Improvements • Evolution speed • Learning speed

  24. ACGP Multiplexer Results Change in local heuristics distribution • Current distribution vs. reference • Distribution: whole population vs. best samples • Reference: first generation vs. previous Change in speed of evolution • Current fitness and number of iterations needed Evolved heuristics • Quantitative and qualitative

  25. Two ACGP Settings • Off-line • Iteration = 25 generations • Can we learn to improve next time? • Can we comprehend knowledge? • In-line, in-between • Iteration = 1, 5, 10 generation • Impact of regrow • Impact on population size

  26. Change in First-order Heuristics Distribution Experiment: • Distribution • whole and best • Reference • first generation • Average of 5 independent runs on single population • Note saturation • just vs. first generation reference or the same vs. previous generation?

  27. Change in First-order Heuristics Distribution Experiment: • Distribution • whole and best • Reference • previous generation

  28. Change in Speed of Evolution Experiment: • simultaneous 5 populations • average shown • adjust every 25 generations • regrow on • update schedule • incremental change in heuristics • Can we be more greedy in heuristics? • can we increase updates to replacements?

  29. Change in Speed of Evolution Experiment: • simultaneous 5 populations • average shown • regrow on • replacement schedule • Is it really so much faster and better? • Note <100%

  30. Change in First-order Heuristics Experiment: • simultaneous 5 populations • average shown • Slow update schedule • Distribution • whole population • Reference • first generation on iteration • Note saturation • learning has saturated

  31. The Evolved First-order Heuristics Experiment: • simultaneous 5 populations • best population shown • slow update schedule • if condition argument • Expected yet strange • only a0, a1, a2, not • a0 high • a2 low but present • a1 missing!!! • Note shift in heuristics

  32. The Evolved First-order Heuristics on not Experiment: • simultaneous 5 populations • best population shown • slow update schedule • not argument • Mystery solved • a1 found high • a2 low additional support • non-recursive

  33. The Evolved First-order Heuristics on action arguments of if Experiment: • simultaneous 5 populations • best population shown • slow update schedule • if action arguments combined • Expected • if high to grow needed deep conditions • data present • others missing

  34. Iteration Length and Regrow

  35. Iteration Length and Regrow

  36. Iteration Length and Regrow

  37. Iteration Length and Regrow

  38. Population Size • Iteration =1, no regrow

  39. Scalability • Library or off-line (long iterations) • Working in the same domain • Working toward harder problems • Mult-11 -> Mult-20 • Reusability of first-order heuristics • Lack of some first-order heuristics • Types will help • On-line (iteration=generation) • Good for solving new problem in a new domain

  40. Another Domain – SantaFe Trail • Interesting and good heuristics evolved • But • Some are good independently but not as a group • Others bad independently but good as a group • Competition between heuristics classes

  41. Current work: ACGP2.1 • CGP2.1 node information • ACGP2.1 extracted heuristics

  42. ACGP2.1 Heuristics • On what: • Type • Functions/Terminals • Combination • What kind: • Zero-order • First-order • Second order

  43. ACGP2.1 Heuristics: Type • First-order on Type • For each type, what type can produce it but each argument individually

  44. ACGP2.1 Heuristics: Type • Second-order on Type • For each type, what can produce it as a family • Note growing complexity

  45. ACGP2.1 Heuristics: Labels • First-order on Labels • For each function, what can label each child individually • The only one in ACGP1.1.1

  46. ACGP2.1 Heuristics: Labels • Second-order on Labels • For each function, what can label the family • Note the growing complexity

  47. ACGP2.1 Heuristics: Combined • Zero-order combined • For each type, what labels (same node) produce it

  48. ACGP2.1 Heuristics: Combined • Zero-order combined • For each function, what types it produces (same node) • Terminals are not overloaded

  49. ACGP2.1 Heuristics: Combined • First-order combined • For each function, and each type it needs to produce, what instances do that

  50. ACGP2.1 Heuristics: Combined • First-order combined • This one really links three levels • Second order would be very complex here

More Related