Optimal feature rescaling in machine learning based on neural networks

Autor:	Vitrò, Federico Maria, Leonesio, Marco, Fagiano, Lorenzo
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Neural and Evolutionary Computing
Druh dokumentu:	Working Paper
Popis:	This paper proposes a novel approach to improve the training efficiency and the generalization performance of Feed Forward Neural Networks (FFNNs) resorting to an optimal rescaling of input features (OFR) carried out by a Genetic Algorithm (GA). The OFR reshapes the input space improving the conditioning of the gradient-based algorithm used for the training. Moreover, the scale factors exploration entailed by GA trials and selection corresponds to different initialization of the first layer weights at each training attempt, thus realizing a multi-start global search algorithm (even though restrained to few weights only) which fosters the achievement of a global minimum. The approach has been tested on a FFNN modeling the outcome of a real industrial process (centerless grinding). Comment: 6 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.10964 Zobrazit plný text záznamu View this record from Arxiv