Genetic Programming IV: Routine Human-Competitive Machine Intelligence

By John R. Koza. 2003

806 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/5ef6bcc28e109a076ea3a30677b349b68889dc44

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review (2005, methodology): “Others have embraced the non-logical nature of scientific discovery and let “random” evolutionary processes be the basis for creative discoveries (Koza et al., 2003).”
Some Empirical Criteria for Attributing Creativity to a Computer Program (2007, background): “Koza et al. (2003) discuss the extent to which genetic programming has been successful as an approach to machine intelligence.”
GP-EndChess: Using Genetic Programming to Evolve Chess Endgame Players (2005, background): “GP has recently been argued to deliver ”high-return, human-competitive machine intelligence” [8].”
Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills (2015, background): “These algorithms have shown impressive performance—often outperforming human engineers [40, 41]—on a range of tasks, such as measuring properties in quantum physics [12], dynamic rocket guidance [42], and robot locomotion [43, 44].”
Statistical strategies for avoiding false discoveries in metabolomics and related experiments (2007, background): “…(2003) gives an excellent example of what may be required, in the context of genetic programming, a technique (e.g. (Koza, 1992; Langdon, 1998; Koza et al., 2003)) that we favour since it gives easily interpretable rules that relate to actual metabolites rather than to latent variables and…”
Illuminating search spaces by mapping elites (2015, background): “Because MAPElites (1) illuminates the relationship between performance and dimensions of interest in solutions, (2) returns a set of high-performing, yet diverse solutions, and (3) improves the state-of-the-art for finding a single, best solution, it will catalyze advances throughout all science and”
Avida (2004, background): “(5) Digital organisms can be used to design solutions to computational problems where it is diﬃcult to write explicit programs that produce the desired behavior [20, 23].”
Automatic programming: The open issue? (2019, background): “Much success lies in the generation of single line functions through Genetic Programming’s application to Symbolic Regression (for example see [58]) and design, for example, in the generation of analogue circuits [33–35], robot morphology [25] and antennae [40].”