Article
Chemistry, Multidisciplinary
Mauro Castelli, Luca Manzoni, Luca Mariot, Giuliamaria Menara, Gloria Pietropolli
Summary: In the field of genetic programming, using a stored evolutionary history in geometric semantic genetic programming (GSGP) can lead to a multi-generational selection scheme that utilizes individuals from older populations, showing improved performance with no additional cost.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Davide Farinati, Illya Bakurov, Leonardo Vanneschi
Summary: This paper investigates the application of dynamic populations in Geometric Semantic Genetic Programming (GSGP) and introduces two novel algorithms. The results of comparative experiments show that these new algorithms perform well in generating robust models.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
I Bakurov, M. Castelli, F. Fontanella, A. Scotto di Freca, L. Vanneschi
Summary: Geometric semantic genetic programming (GSGP) is a variant of genetic programming that transforms the landscape of any supervised regression problem into a unimodal error surface. In a previous study, a novel variant of GSGP was proposed for binary classification problems, which showed promising performance by using a logistic-based activation function to constrain the output value. This paper presents the results of 18 test problems and compares them with other well-known classification schemes, demonstrating the effectiveness of the proposed approach.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Edgar Galvan, Leonardo Trujillo, Fergal Stapleton
Summary: This study proposes a method to introduce semantic-based distance in Multi-objective Genetic Programming to promote semantic diversity. When using highly unbalanced binary classification problems, this method can generate more non-dominated solutions and improve diversity, showing more statistically significant results compared to the other four methods.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Claudia N. Sanchez, Mario Graff
Summary: This paper proposes a method to guide the learning process of genetic programming using individual semantics, and performs parent selection using heuristics. The experimental results show that the combination of parent selection based on agreement and random selection performs better on multiple classification problems.
EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Software Engineering
Leonardo Trujillo, Jose Manuel Munoz Contreras, Daniel E. Hernandez, Mauro Castelli, Juan J. Tapia
Summary: Geometric Semantic Genetic Programming (GSGP) is an efficient machine learning method based on evolutionary computation, which performs search operations at the level of program semantics. This paper introduces GSGP-CUDA, the first CUDA implementation of GSGP that exploits the parallelism of GPUs, resulting in significant speedups during the model training process. Additionally, the implementation allows seamless inference over new data using the best evolved model.
Article
Computer Science, Software Engineering
Jesse Heyninck, Bart Bogaerts
Summary: Approximation fixpoint theory (AFT) is an abstract and general algebraic framework for studying the semantics of non-monotonic logics. In recent work, AFT was extended to non-deterministic operators, which have sets of elements as their range. This paper contributes to non-deterministic AFT by defining and studying ultimate approximations of non-deterministic operators, providing an algebraic formulation of the semi-equilibrium semantics, and generalizing the characterizations of disjunctive logic programs to disjunctive logic programs with aggregates.
THEORY AND PRACTICE OF LOGIC PROGRAMMING
(2023)
Article
Computer Science, Artificial Intelligence
Qi Chen, Bing Xue, Mengjie Zhang
Summary: The research introduces a new entropy-based diversity measure for genetic programming, aiming to assist in achieving a balance between exploration and exploitation, thus enhancing learning and generalization performance.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Liang Yi-Fan, Liu Chang, Wang Han-Rui, Liu Kun-Hong, Yao Jun-Feng, She Ying-Ying, Dai Gui-Ming, Yuna Okina
Summary: This paper proposes a new method, TOGP-ECOC, based on Genetic Programming to generate effective ECOC codematrix, which outperforms other ECOC algorithms on various data sets. The experiments confirm the superiority of the algorithm in improving performance of multiclass classification tasks.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Baligh Al-Helali, Qi Chen, Bing Xue, Mengjie Zhang
Summary: This research leverages transfer learning and genetic programming to address the lack of knowledge caused by data incompleteness, proposing a new multitree GP-based feature construction method for TL in symbolic regression. The method transfers knowledge about the importance of features and instances from the source domain to the target domain to improve learning performance, and develops new genetic operators and probabilistic crossovers.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Software Engineering
Beatriz Brito Oliveira, Maria Antonia Carravilla, Jose Fernando Oliveira, Mauricio G. C. Resende
Summary: This paper presents a C++ application programming interface for a co-evolutionary algorithm in stochastic problems, based on a biased random-key genetic algorithm involving solution and scenario populations that mutually impact each other through fitness calculations.
OPTIMIZATION METHODS & SOFTWARE
(2022)
Article
Computer Science, Artificial Intelligence
Vincent Barichard
Summary: This article introduces CHR++, an implementation of CHR in C++ that is efficient, user-friendly, and supports don't know non-determinism. CHR++ conforms to the refined semantics of CHR and provides a high-level syntax similar to Prolog. It is a powerful and optimized system that can tackle a specific class of problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Mathematics, Applied
Bartlomiej Jacek Kubica
Summary: This paper introduces the ADHC library developed by the author, which has several unique features and is particularly useful for interval-related applications. The paper describes the library's features, focusing on the new ones added in version 2.0, and compares its efficiency with other packages. Examples of ADHC applications are given, including solving nonlinear systems and applications related to modern machine learning. The paper also outlines and discusses planned extensions and possible directions for future development of ADHC.
NUMERICAL ALGORITHMS
(2023)
Article
Computer Science, Artificial Intelligence
Ying Bi, Bing Xue, Mengjie Zhang
Summary: A new Genetic Programming based approach is proposed in this article for automatically learning informative features for different image classification tasks. The approach uses a flexible program structure to evolve solutions of variable depths, extracting various numbers and types of features from images. The results demonstrate that the new approach achieves better classification performance than most benchmark methods.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Mathematics, Applied
Philip T. Gressman
Summary: This paper systematically studies a class of geometric integral inequalities, which play a significant role in continuum combinatorial approaches to improve L-p inequalities for Radon-like transformations over polynomial submanifolds. These desired inequalities are related to and extend important results in geometric measure theory.