A novel data-driven statistical learning algorithm for neural networks applied to language translation
Authors:
- Juan German Hernández SánchezJSJuan German Hernández Sánchez
- José Manuel Cruz OlguínJOJosé Manuel Cruz Olguín
- Salvador Santos RomeroSRSalvador Santos Romero
- Anilú Franco ÁrcegaAÁAnilú Franco Árcega
- Virgilio López MoralesVMVirgilio López Morales
- Manuel Alejandro Ojeda MissesMMManuel Alejandro Ojeda Misses
Preprint
- 19 August 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
This article presents a novel statistical data-driven learning algorithm for neural network training, designed for low-resource data scenarios. The proposed method employs statistical descriptors, including the sample mean, standard deviation, z-score, and normal distribution, to estimate the probability of prediction error and guide the adaptive updating of weights and biases. By incorporating error normalization and probabilistic mappings, the algorithm provides a statistically guided learning mechanism that accounts for signal variability while promoting stable convergence. Contrasting conventional approaches that rely primarily on gradient information, the proposed framework uses probabilistic information derived from the distribution of error to regulate parameter adaptation. The methodology is validated using Nahuatl–Spanish lexical translation task implemented with neural networks. • Proposes a statistical–probabilistic learning algorithm that uses error distributions instead of relying only on gradients.• The method is intended for low-resource scenarios and shows stable convergence under the evaluated conditions.• Validated on a Nahuatl–Spanish lexical translation task using a multilayer neural network with comparable performance than classical methods.Keywords
This publication has 22 references indexed in Scilit:
- Global quantitative robustness of regression feed-forward neural networksNeural Computing and Applications, 2024
- Performance analysis of hybrid deep learning framework using a vision transformer and convolutional neural network for handwritten digit recognitionMethodsX, 2024
- A survey of uncertainty in deep neural networksArtificial Intelligence Review, 2023
- Analysis of ECG-based arrhythmia detection system using machine learningMethodsX, 2023
- LogNNet model as a fast, simple and economical AI instrument in the diagnosis and prognosis of COVID-19MethodsX, 2023
- A non-dominated sorting based multi-objective neural network algorithmMethodsX, 2023
- Uncertainty quantification in scientific machine learning: Methods, metrics, and comparisonsJournal of Computational Physics, 2023
- A review of uncertainty quantification in deep learning: Techniques, applications and challengesInformation Fusion, 2021
- Gradient descent optimizes over-parameterized deep ReLU networksMachine Learning, 2019
- A Survey of Deep Learning and Its Applications: A New Paradigm to Machine LearningArchives of Computational Methods in Engineering, 2019