Zobrazeno 1 - 10
of 137
pro vyhledávání: '"Langdon, William B"'
Autor:
Gong, Jingzhi, Li, Sisi, d'Aloisio, Giordano, Ding, Zishuo, Ye, Yulong, Langdon, William B., Sarro, Federica
Tuning the parameters and prompts for improving AI-based text-to-image generation has remained a substantial yet unaddressed challenge. Hence we introduce GreenStableYolo, which improves the parameters and prompts for Stable Diffusion to both reduce
Externí odkaz:
http://arxiv.org/abs/2407.14982
By their very name caches are often overlooked and yet play a vital role in the performance of modern and indeed future hardware. Using MAGPIE (Machine Automated General Performance Improvement via Evolution of software) we show genetic improvement G
Externí odkaz:
http://arxiv.org/abs/2304.03235
Autor:
Langdon, William B.
We inject a random value into the evaluation of highly evolved deep integer GP trees 9743720 times and find 99.7percent Suggesting crossover and mutation's impact are dissipated and seldom propagate outside the program. Indeed only errors near the ro
Externí odkaz:
http://arxiv.org/abs/2204.13997
Autor:
LANGDON, WILLIAM B. V. will.langdon12@gmail.com, HAMMOND, JAMES E.
Publikováno v:
Entomologist's Record & Journal of Variation. May/Jun2024, Vol. 136 Issue 3, p122-125. 4p.
Autor:
LANGDON, WILLIAM B. V. will.langdon12@gmail.com
Publikováno v:
Entomologist's Record & Journal of Variation. May/Jun2024, Vol. 136 Issue 3, p107-118. 12p.
Autor:
LANGDON, WILLIAM B. V.
Publikováno v:
Entomologist's Record & Journal of Variation. Mar/Apr2024, Vol. 136 Issue Part 2, p65-70. 6p.
Autor:
LANGDON, WILLIAM B. V. will.langdon12@gmail.com
Publikováno v:
Entomologist's Record & Journal of Variation. Jan/Feb2024, Vol. 136 Issue Part1, p8-24. 17p.
Autor:
Langdon, William B., Weimer, Westley, Petke, Justyna, Fredericks, Erik, Lee, Seongmin, Winter, Emily, Basios, Michail, Cohen, Myra B., Blot, Aymeric, Wagner, Markus, Bruce, Bobby R., Yoo, Shin, Gerasimou, Simos, Krauss, Oliver, Huang, Yu, Gerten, Michael
Following Prof. Mark Harman of Facebook's keynote and formal presentations (which are recorded in the proceedings) there was a wide ranging discussion at the eighth international Genetic Improvement workshop, GI-2020 @ ICSE (held as part of the 42nd
Externí odkaz:
http://arxiv.org/abs/2007.15987
Autor:
Langdon, William B.
random_tree() is a linear time and space C++ implementation able to create trees of up to a billion nodes for genetic programming and genetic improvement experiments. A 3.60GHz CPU can generate more than 18 million random nodes for GP program trees p
Externí odkaz:
http://arxiv.org/abs/2001.04505