1. Case Injected Genetic Algorithms Sushil J. Louis Genetic Algorithm Systems Lab (gaslab) University of Nevada, Reno http://www.cs.unr.edu/~sushil http://gaslab.cs.unr.edu/ sushil@cs.unr.edu

2. Learning from Experience: Case Injected Genetic Algorithm Design of Combinational Logic Circuits Sushil J. Louis Genetic Algorithm Systems Lab (gaslab) University of Nevada, Reno http://www.cs.unr.edu/~sushil http://gaslab.cs.unr.edu/ sushil@cs.unr.edu

3. http://gaslab.cs.unr.edu Outline  Motivation  What is the technique? Genetic Algorithm and Case-Based Reasoning  Is it useful? Evaluate performance on Combinational Logic Design  Results  Conclusions

4. http://gaslab.cs.unr.edu Outline  Motivation  What is the technique? Genetic Algorithm and Case-Based Reasoning  Is it useful? Combinational Logic Design Strike Force Asset Allocation TSP Scheduling  Conclusions

5. http://gaslab.cs.unr.edu Genetic Algorithm  Non-Deterministic, Parallel, Search  Poorly understood problems  Evaluate, Select, Recombine  Population search Population member encodes candidate solution Building blocks combine to make progress More resistant to local optima Iterative, requiring many evaluations

6. http://gaslab.cs.unr.edu Motivation  Deployed systems are expected to confront and solve many problems over their lifetime  How can we increase genetic algorithm performance with experience?  Provide GA with a memory

7. http://gaslab.cs.unr.edu Case-Based Reasoning  When confronted by a new problem, adapt similar (already solved) problem’s solution to solve new problem  CBR  Associative Memory + Adaptation  CBR: Indexing (on problem similarity) and adaptation are domain dependent

8. http://gaslab.cs.unr.edu Case Injected Genetic AlgoRithm  Combine genetic search with case-based reasoning  Case-base provides memory  Genetic algorithm provides adaptation  Genetic algorithm generates cases Any member of the GA’s population is a case

9. http://gaslab.cs.unr.edu System

10. http://gaslab.cs.unr.edu Related work  Seeding:Koza, Greffensttette, Ramsey, Louis  Lifelong learning: Thrun  Key Differences Store and reuse intermediate solutions Solve sequences of similar problems

11. http://gaslab.cs.unr.edu Combinational Logic Design  An example of configuration design  Given a function and a target technology to work with design an artifact that performs this function subject to constraints Target technology: Logic gates Function: Parity checking Constraints: 2-D gate array

12. http://gaslab.cs.unr.edu Encoding

13. http://gaslab.cs.unr.edu Encoding

14. http://gaslab.cs.unr.edu Parity Input3-bit Parity3-1 problem 00000 00110 01011 01100 10011 10100 11000 11111

15. http://gaslab.cs.unr.edu Which cases to inject?  Problem distance metric (Louis ‘97) Domain dependent  Solution distance metric Genetic algorithm encodings Binary – hamming distance Real – euclidean distance Permutation – longest common substring …

16. http://gaslab.cs.unr.edu Problem similarity

17. http://gaslab.cs.unr.edu Lessons  Storing and Injecting solutions may not improve solution quality  Storing and Injecting partial solutions does lead to improved quality

18. http://gaslab.cs.unr.edu OSSP Performance

19. http://gaslab.cs.unr.edu Solution Similarity

20. http://gaslab.cs.unr.edu Periodic Injection Strategies  Closest to best  Furthest from worst  Probabilistic closest to best  Probabilistic furthest from worst  Randomly choose a case from case-base  Create random individual

21. http://gaslab.cs.unr.edu Setup  50, 6-bit combinational logic design problems  Randomly select and flip bits in parity output to define logic function  Compare performance Quality of final design solution (correct output) Time to this final solution (in generations)

22. http://gaslab.cs.unr.edu Parameters  Population size: 30  No of generations: 30  CHC (elitist) selection  Scaling factor: 1.05  Prob. Crossover: 0.95  Prob. Mutation: 0.05  Store best individual every generation  Inject every 5 generations (2^5 = 32)  Inject 3 cases (10%)  Multiple injection strategies Averages over 10 runs

23. http://gaslab.cs.unr.edu Problem distribution

24. http://gaslab.cs.unr.edu Performance - Quality

25. http://gaslab.cs.unr.edu Performance - Time

26. http://gaslab.cs.unr.edu Injection Strategies

27. http://gaslab.cs.unr.edu Solution distribution

28. http://gaslab.cs.unr.edu Strike force asset allocation  Allocate platforms to targets  Dynamic Changing Priority Battlefield conditions Popup Weather …

29. http://gaslab.cs.unr.edu Factors in allocation  Pilot proficiency  Asset suitability  Priority  Risk Route Other assets (SEAD) Weather

30. http://gaslab.cs.unr.edu Maximize mission success  Binary encoding  Platform to multiple targets  Target can have multiple platforms  Dynamic battle-space Strong time constraints

31. http://gaslab.cs.unr.edu Setup  50 problems.  10 platforms, 40 assets, 10 targets  Each platform could be allocated to two targets  Problems varied in risk matrix  Popsize=80, Generations=80, Pc=1.0, Pm=0.05, probabilistic closest to best, injection period=9, injection % = 10% of popsize

32. http://gaslab.cs.unr.edu Results

33. http://gaslab.cs.unr.edu TSP  Find the shortest route that visits every city exactly once (except for start city)  Permutation encoding. Ex: 35412  Similarity metric: Longest common subsequence (Cormen et al, Introduction to Algorithms)  50 problems, move city locations

34. http://gaslab.cs.unr.edu TSP performance

35. http://gaslab.cs.unr.edu Scheduling  Job shop scheduling problems  Permutation encoding (Fang)  Similarity metric: Longest common subsequence (Cormen et al, Introduction to Algorithms)  50 problems, change task lengths

36. http://gaslab.cs.unr.edu JSSP Performance (10x10)

37. http://gaslab.cs.unr.edu JSSP Performance (15x15)

38. http://gaslab.cs.unr.edu Summary  Case Injected Genetic AlgoRithm: A hybrid system that combines genetic algorithms with a case-based memory  Defined problem-similarity and solution- similarity metrics  Defined performance metrics and showed empirically that CIGAR learns to increase performance for sequences of similar problems

39. http://gaslab.cs.unr.edu Conclusions  Case Injected Genetic AlgoRithm is a viable system for increasing performance with experience  Implications for system design Increases performance with experience Generates cases during problem solving Long term navigable store of expertise Design analysis by analyzing case-base