Learning based on neurovectors for tabular data: a new neural network approach
This addresses the problem of interpretability and efficiency in neural networks for tabular data, though it appears incremental as it builds on existing neural network concepts.
The paper tackles tabular data processing by introducing Neurovectors, a novel paradigm that uses vector relationships and energy propagation instead of traditional backpropagation, resulting in competitive accuracy on classification and regression tasks from UCI and Kaggle datasets.
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.