Search-based procedural content generation: A taxonomy and survey

J Togelius, GN Yannakakis, KO Stanley… - IEEE Transactions on …, 2011 - ieeexplore.ieee.org
The focus of this survey is on research in applying evolutionary and other metaheuristic
search algorithms to automatically generating content for games, both digital and nondigital …

Evolutionary computation and structural design: A survey of the state-of-the-art

R Kicinger, T Arciszewski, K De Jong - Computers & structures, 2005 - Elsevier
Evolutionary computation is emerging as a new engineering computational paradigm, which
may significantly change the present structural design practice. For this reason, an extensive …

Evolution through large models

J Lehman, J Gordon, S Jain, K Ndousse, C Yeh… - … of Evolutionary Machine …, 2023 - Springer
This chapter pursues the insight that large language models (LLMs) trained to generate
code can vastly improve the effectiveness of mutation operators applied to programs in …

Best practices for comparing optimization algorithms

V Beiranvand, W Hare, Y Lucet - Optimization and Engineering, 2017 - Springer
Comparing, or benchmarking, of optimization algorithms is a complicated task that involves
many subtle considerations to yield a fair and unbiased evaluation. In this paper, we …

A hypercube-based encoding for evolving large-scale neural networks

KO Stanley, DB D'Ambrosio, J Gauci - Artificial life, 2009 - direct.mit.edu
Research in neuroevolution—that is, evolving artificial neural networks (ANNs) through
evolutionary algorithms—is inspired by the evolution of biological brains, which can contain …

Experience-driven procedural content generation

GN Yannakakis, J Togelius - IEEE Transactions on Affective …, 2011 - ieeexplore.ieee.org
Procedural content generation (PCG) is an increasingly important area of technology within
modern human-computer interaction (HCI) design. Personalization of user experience via …

Compositional pattern producing networks: A novel abstraction of development

KO Stanley - Genetic programming and evolvable machines, 2007 - Springer
Natural DNA can encode complexity on an enormous scale. Researchers are attempting to
achieve the same representational efficiency in computers by implementing developmental …

A taxonomy for artificial embryogeny

KO Stanley, R Miikkulainen - Artificial life, 2003 - ieeexplore.ieee.org
A major challenge for evolutionary computation is to evolve phenotypes such as neural
networks, sensory systems, or motor controllers at the same level of complexity as found in …

Evolutionary design of neural network architectures: a review of three decades of research

HT Ünal, F Başçiftçi - Artificial Intelligence Review, 2022 - Springer
We present a comprehensive review of the evolutionary design of neural network
architectures. This work is motivated by the fact that the success of an Artificial Neural …

Picbreeder: A case study in collaborative evolutionary exploration of design space

J Secretan, N Beato, DB D'Ambrosio… - Evolutionary …, 2011 - ieeexplore.ieee.org
For domains in which fitness is subjective or difficult to express formally, interactive
evolutionary computation (IEC) is a natural choice. It is possible that a collaborative process …