Accelerating Genetic Programming using GPUs

Vimarsh, Sathia,; Ganesh, Venkataramana; Thejaswi, Nanditale, Shankara Rao

doi:10.48550/arxiv.2110.11226

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the applicability of SR may vary depending on dataset characteristics, necessitating investigations into its adaptability to diverse domains and computational properties of the dataset [56,91]. Additionally, this study solely employed one SR method-the GPlearn model [29]. Further exploration of other SR models (as proposed in [56]) could yield different results and pave the way for a meta-learning-based approach to select the best SR model based on dataset characteristics [9].…”

Section: Discussionmentioning

confidence: 99%

“…Consistent with common data-driven model development practices, we initially divide the rows into training and validation subsets. Focusing on the training subset to avoid data leakage [76], we employ the well-known GPlearn SR model [29] to create multiple SR models for the training data, each one contributing a potential feature to X * . Each instance of the SR model is characterized by a distinct parsimony coefficient.…”

Section: Sr As Fementioning

confidence: 99%

“…To evaluate this method's performance, we employ an 'off-the-shelf ' SR model (GPlearn [29]), automatic ML (AutoML) (Tree-based Pipeline Optimization Tool (TPOT) [30]), and automatic DL models (AutoKeras [31]) on both synthetic and real-world datasets. We investigate how the introduction of SR-derived features impacts the performance of data-driven models while reducing the reliance on developer expertise.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Symbolic regression as a feature engineering method for machine and deep learning regression tasks

Shmuel,

Glickman,

Lazebnik

2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

In the realm of machine and deep learning regression tasks, the role of effective feature engineering (FE) is pivotal in enhancing model performance. Traditional approaches of FE often rely on domain expertise to manually design features for machine learning models. In the context of deep learning models, the FE is embedded in the neural network's architecture, making it hard for interpretation. In this study, we propose to integrate symbolic regression (SR) as an FE process before a machine learning model to improve its performance. We show, through extensive experimentation on synthetic and 21 real-world datasets, that the incorporation of SR-derived features significantly enhances the predictive capabilities of both machine and deep learning regression models with 34-86% root mean square error (RMSE) improvement in synthetic datasets and 4-11.5\% improvement in real-world datasets. In an additional realistic use case, we show the proposed method improves the machine learning performance in predicting superconducting critical temperatures based on Eliashberg theory by more than 20% in terms of RMSE. These results outline the potential of SR as an FE component in data-driven models, improving them in terms of performance and interpretability.

show abstract