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

TL;DR

This paper introduces Neurovectors, a novel neural network paradigm for tabular data that encodes information in vector spaces, offering improved interpretability and efficiency over traditional models.

Contribution

It presents a new Neurovector-based learning approach that structures data via interconnected vectors, differing from weight-based neural networks, and demonstrates competitive performance.

Findings

Neurovectors achieve accuracy comparable to standard models.

The approach enhances interpretability of the learning process.

Experimental results validate effectiveness on benchmark datasets.

Abstract

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. To evaluate its performance, we compare our approach with standard machine learning and deep learning models, showing that Neurovectors achieve competitive accuracy.