Learning based on neurovectors for tabular data: a new neural network approach

--In this paper, we present a novel learning approach based on Neurovectors, an innovative paradigm that structures information through interconnected nodes and vector relationships for tabular data processing. Unlike traditional artificial neural networks that rely on weight adjustment through backpropagation, Neurovectors encode information by structuring data in vector spaces where energy propagation, rather than traditional weight updates, drives the learning process, enabling a more adaptable and explainable learning process. Our method generates dynamic representations of knowledge through neurovectors, thereby improving both the interpretability and efficiency of the predictive model. Experimental results using datasets from well-established repositories such as the UCI machine learning repository and Kaggle are reported both for classification and regression. T o evaluate its performance, we compare our approach with standard machine learning and deep learning models, showing that Neurovectors achieve competitive accuracy while significantly reducing computational costs. Machine learning has significantly advanced in recent decades, with models such as deep neural networks (DNNs), decision tree-based methods, and probabilistic models [1], [2], among others. Despite their widespread success, these approaches present limitations in terms of preprocessing requirements, interpretability, and computational efficiency. Deep neural networks have demonstrated remarkable performance in various domains--from computer vision to natural language processing [3].