Parallel Ant Programming using genetic operators

Hara, Akira; Kushida, Jun-ichi; Tanabe, Souichi; Takahama, Tetsuyuki

doi:10.1109/iwcia.2013.6624788

Cited by 2 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, many hybridizations of SI with other automatic programming techniques can be found in the literature, for many goals: self‐adapt the mutation rate in linear GP, improve the power of crossover operator in GP, optimize GP‐evolved arithmetic classifier expressions, optimize parameters and connected weights of ANNs, etc. However, to our knowledge, only one proposal exists the other way round, presented by Hara et al, where genetic operators were used to change the structure of individuals in AP. It would be interesting to explore the combination of SP with other techniques to improve their performance in specific domains, as the combination of concepts from several metaheuristics allows to take advantage of the strengths of each one, as it has been demonstrated so far with applications in several fields.…”

Section: Open Issuesmentioning

confidence: 99%

“…connected weights of ANNs, 132 etc. However, to our knowledge, only one proposal exists the other way round, presented by Hara et al 48 , where genetic operators were used to change the structure of individuals in AP. It would be interesting to explore the combination of SP with other techniques to improve their performance in specific domains, as the combination of concepts from several metaheuristics allows to take advantage of the strengths of each one, as it has been demonstrated so far with applications in several fields.…”

Section: Open Issuesmentioning

confidence: 99%

“…The most recent AP proposal having individuals encoded by prototype trees was presented by Hara et al In this work, the authors introduced genetic operators to change the structure of the trees during the run of the algorithm with the aim of avoiding premature convergence. They compared the performance of their technique against that obtained by Roux and Fonlupt's original algorithm, obtaining better results in two symbolic regression problems and the even‐5‐parity problem.…”

Section: The Ap Metaheuristicmentioning

confidence: 99%

See 2 more Smart Citations

Swarm‐based metaheuristics in automatic programming: a survey

Olmo

Romero

Ventura

2014

WIREs Data Min & Knowl

View full text Add to dashboard Cite

On the one hand, swarm intelligence (SI) is an emerging field of artificial intelligence that takes inspiration in the collective and social behavior of different groups of simple agents. On the other hand, the automatic evolution of programs is an active research area that has attracted a lot of interest and has been mostly promoted by the genetic programming paradigm. The main objective is to find computer programs from a high‐level problem statement of what needs to be done, without needing to know the structure of the solution beforehand. This paper looks at the intersection between SI and automatic programming, providing a survey on the state‐of‐the‐art of the automatic programming algorithms that use an SI metaheuristic as the search technique. The expression of swarm programming (SP) has been coined to cover swarm‐based automatic programming proposals, since they have been published to date in a disorganized manner. Open issues for future research are listed. Although it is a very recent area, we hope that this work will stimulate the interest of the research community in the development of new SP metaheuristics, algorithms, and applications. WIREs Data Mining Knowl Discov 2014, 4:445–469. doi: 10.1002/widm.1138 This article is categorized under: Algorithmic Development > Association Rules Technologies > Classification Technologies > Computational Intelligence

show abstract

Section: Open Issuesmentioning

confidence: 99%

Section: Open Issuesmentioning

confidence: 99%

Section: The Ap Metaheuristicmentioning

confidence: 99%

See 1 more Smart Citation

Swarm‐based metaheuristics in automatic programming: a survey

Olmo

Romero

Ventura

2014

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

Enhancing Program Synthesis with Large Language Models Using Many-Objective Grammar-Guided Genetic Programming

Tao,

Ventresque,

Nallur

et al. 2024

Algorithms

View full text Add to dashboard Cite

The ability to automatically generate code, i.e., program synthesis, is one of the most important applications of artificial intelligence (AI). Currently, two AI techniques are leading the way: large language models (LLMs) and genetic programming (GP) methods—each with its strengths and weaknesses. While LLMs have shown success in program synthesis from a task description, they often struggle to generate the correct code due to ambiguity in task specifications, complex programming syntax, and lack of reliability in the generated code. Furthermore, their generative nature limits their ability to fix erroneous code with iterative LLM prompting. Grammar-guided genetic programming (G3P, i.e., one of the top GP methods) has been shown capable of evolving programs that fit a defined Backus–Naur-form (BNF) grammar based on a set of input/output tests that help guide the search process while ensuring that the generated code does not include calls to untrustworthy libraries or poorly structured snippets. However, G3P still faces issues generating code for complex tasks. A recent study attempting to combine both approaches (G3P and LLMs) by seeding an LLM-generated program into the initial population of the G3P has shown promising results. However, the approach rapidly loses the seeded information over the evolutionary process, which hinders its performance. In this work, we propose combining an LLM (specifically ChatGPT) with a many-objective G3P (MaOG3P) framework in two parts: (i) provide the LLM-generated code as a seed to the evolutionary process following a grammar-mapping phase that creates an avenue for program evolution and error correction; and (ii) leverage many-objective similarity measures towards the LLM-generated code to guide the search process throughout the evolution. The idea behind using the similarity measures is that the LLM-generated code is likely to be close to the correct fitting code. Our approach compels any generated program to adhere to the BNF grammar, ultimately mitigating security risks and improving code quality. Experiments on a well-known and widely used program synthesis dataset show that our approach successfully improves the synthesis of grammar-fitting code for several tasks.

show abstract

Parallel Ant Programming using genetic operators

Cited by 2 publications

References 9 publications

Swarm‐based metaheuristics in automatic programming: a survey

Swarm‐based metaheuristics in automatic programming: a survey

Enhancing Program Synthesis with Large Language Models Using Many-Objective Grammar-Guided Genetic Programming

Contact Info

Product

Resources

About