%0 Journal Article %1 daida:2001:GPEM %A Daida, Jason M. %A Bertram, Robert R. %A Stanhope, Stephen A. %A Khoo, Jonathan C. %A Chaudhary, Shahbaz A. %A Chaudhri, Omer A. %A Polito II, John A. %D 2001 %J Genetic Programming and Evolvable Machines %K GP algorithms, difficulty, fitness genetic landscapes, problem problems, programming, test theory %N 2 %P 165--191 %R doi:10.1023/A:1011504414730 %T What Makes a Problem GP-Hard? Analysis of a Tunably Difficult Problem in Genetic Programming %V 2 %X This paper addresses the issue of what makes a problem genetic programming (GP)-hard by considering the binomial-3 problem. In the process, we discuss the efficacy of the metaphor of an adaptive fitness landscape to explain what is GP-hard. We indicate that, at least for this problem, the metaphor is misleading.

@article{daida:2001:GPEM, abstract = {This paper addresses the issue of what makes a problem genetic programming (GP)-hard by considering the binomial-3 problem. In the process, we discuss the efficacy of the metaphor of an adaptive fitness landscape to explain what is GP-hard. We indicate that, at least for this problem, the metaphor is misleading.}, added-at = {2008-06-19T17:35:00.000+0200}, author = {Daida, Jason M. and Bertram, Robert R. and Stanhope, Stephen A. and Khoo, Jonathan C. and Chaudhary, Shahbaz A. and Chaudhri, Omer A. and {Polito II}, John A.}, biburl = {https://www.bibsonomy.org/bibtex/2602f70eaf4afc7ef724e39687072c8e4/brazovayeye}, broken = {http://ipsapp009.lwwonline.com/content/getfile/4723/5/5/fulltext.pdf}, doi = {doi:10.1023/A:1011504414730}, interhash = {d0aefedb3ed1a6b52da70c6327d24d3f}, intrahash = {602f70eaf4afc7ef724e39687072c8e4}, issn = {1389-2576}, journal = {Genetic Programming and Evolvable Machines}, keywords = {GP algorithms, difficulty, fitness genetic landscapes, problem problems, programming, test theory}, month = {June}, notes = {patched lilgp. Mersenne Twister. Size and Shape of solutions to 3 binomial - tunably difficult by changing random constants used. Edvard Munch Scream. Inconsistency of ERC value within parse tree context. Destructive crossover. P180 {"}the fitness function did not need to be rugged for GP to encounter difficulty.{"} GP as error correcting. Mathematica. p186 {"}increased population meant more individuals gathered around the{"} suboptimal {"}0.8 attractor{"}. Article ID: 335714}, number = 2, pages = {165--191}, timestamp = {2008-06-19T17:38:21.000+0200}, title = {What Makes a Problem {GP}-Hard? Analysis of a Tunably Difficult Problem in Genetic Programming}, volume = 2, year = 2001 }