Download
genetic algorithms in problem solving n.
Skip this Video
Loading SlideShow in 5 Seconds..
Genetic Algorithms in Problem Solving PowerPoint Presentation
Download Presentation
Genetic Algorithms in Problem Solving

Genetic Algorithms in Problem Solving

123 Views Download Presentation
Download Presentation

Genetic Algorithms in Problem Solving

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

  1. Genetic Algorithms in Problem Solving 1998년 7월 16일 조 동 연

  2. EVOLVING COMPUTER PROGRAMS (1) • Evolving Lisp Programs • Kepler’s Third Law: P2 = cA3 PROGRAM ORBITAL_PERIORD C # Mars # A = 1.52 P = SQRT(A * A * A) PRINT P END ORBITAL_PERIORD (defun orbital_period () ; Mars ; (setf A 1.52) (sqrt (* A (* A A))))

  3. EVOLVING COMPUTER PROGRAMS (2) • Koza’s algorithm - Genetic Programming (GP) 1. Choose a set of possible functions and terminals for the program. F = {+, - *, /,  }, T = {A} 2. Generate an initial population of random trees (programs) using the set of possible functions and terminals. 3. Calculate the fitness of each program in the population by running it on a set of “fitness cases” (a set of input for which the correct output is known). 4. Apply selection, crossover, and mutation to the population to form a new population. 5. Steps 3 and 4 are repeated for some number of generations.

  4. EVOLVING COMPUTER PROGRAMS (3)

  5. EVOLVING COMPUTER PROGRAMS (4) • Block-Stacking Problem • T = {CS, TB, NN} • F = {MS(x), MT(x), DU(exp1, exp2), NOT(exp1), EQ(exp1, exp2) } • (EQ (DU (MT CS) (NOT CS)) (DU (MS NN) (NOT NN)))

  6. EVOLVING COMPUTER PROGRAMS (5) • Evolving Cellular Automata (CA) • Example (N=11, radius = 1) • space-time diagram Rule table: neighborhood: 000 001 010 011 100 101 110 111 output bit : 0 0 0 1 0 1 1 1 Lattice: t = 0 1 0 1 0 0 1 1 1 0 1 0 t = 1 0 1 0 0 0 1 1 1 1 0 1

  7. EVOLVING COMPUTER PROGRAMS (6) • Density-classification task (N=149, r =3)

  8. DATA ANALYSIS AND PREDICTION (1) • Predicting Dynamical Systems • individual • C = {($20  Price of Xerox Stock on day 1) ^ ($25  Price of Xerox Stock on day 2  $27) ^ ($22  Price of Xerox Stock on day 3  $25)} • crossover, mutation

  9. DATA ANALYSIS AND PREDICTION (2)

  10. DATA ANALYSIS AND PREDICTION (3) • Predicting Protein Structure

  11. EVOLVING NEURAL NETWORKS (1)

  12. EVOLVING NEURAL NETWORKS (2) • Evolving Weights in a Fixed Network

  13. EVOLVING NEURAL NETWORKS (3)

  14. EVOLVING NEURAL NETWORKS (4) • Evolving Network Architectures • Direct Encoding

  15. EVOLVING NEURAL NETWORKS (5) • Grammatical Encoding