Decoding Artificial Intelligence: A Tutorial on Neural Networks in Behavioral Research
Open Access
- 2 July 2025
- journal article
- Published by Colegio Oficial de la Psicologia de Madrid in Clinical and Health
- Vol. 36 (2) , 77-95
Abstract
Background: Artificial Neural Networks (ANNs), particularly multilayer perceptrons (MLPs) with backpropagation, are increasingly used in Behavioral and Health Sciences for data analysis. This paper provides a comprehensive tutorial on implementing backpropagation in MLP models for regression and classification tasks using Python. Method: The tutorial guides readers step-by-step through building a backpropagation MLP using a simulated data matrix (N = 1,000) with psychological variables, demonstrating ANNs’ versatility in predicting continuous variables and classifying (binary and polytomous) patterns. Python scripts and detailed output interpretations are included. Results: MLP models trained with backpropagation show effectiveness in regression (R² = .71) and classification (binary AUC = .93, polytomous AUC range: .81-.93) on test sets. Conclusions: This tutorial aims to demystify ANNs and promote their use in Behavioral and Health Sciences and other fields, bridging the gap between theory and practical implementation. Introducción:, Las Redes Neuronales Artificiales (RNA), especialmente los perceptrones multicapa (MLPs) con retropropagación, son cada vez más utilizadas en Ciencias del Comportamiento y de la Salud para analizar datos. Este artículo presenta un tutorial completo sobre la implementación de modelos MLP con retropropagación para tareas de regresión y clasificación usando Python. ,Método:, El tutorial guía paso a paso la construcción de un MLP con retropropagación utilizando una matriz de datos simulados (,N, = 1,000) con variables psicológicas, demostrando la versatilidad de las RNA en la predicción de variables continuas y clasificación de (binarios y politómicos). Se incluyen scripts de Python y su interpretación detallada. ,Resultados:, Los modelos MLP muestran eficacia en regresión (,R,² = 0.71) y clasificación (AUC binaria = .93, rango AUC politómica: .81-.93) en los tests. ,Conclusiones:, Este tutorial persigue desmitificar las RNA y promover su uso en Ciencias del Comportamiento y la Salud, facilitando la transición de la teoría a la práctica.Keywords
This publication has 25 references indexed in Scilit:
- Interpretable machine learning for psychological research: Opportunities and pitfalls.Psychological Methods, 2025
- Impacts of user-generated images in online reviews on customer engagement: A panel data analysisTourism Management, 2023
- An introductory guide for conducting psychological research with big data.Psychological Methods, 2023
- Deep learning models to study sentence comprehension in the human brainLanguage, Cognition and Neuroscience, 2023
- Coding infant engagement in the Face-to-Face Still-Face paradigm using deep neural networksInfant Behavior and Development, 2023
- Intuitive physics learning in a deep-learning model inspired by developmental psychologyNature Human Behaviour, 2022
- In living color? Understanding the importance of color complexity in listing images for accommodation sharingTourism Management, 2022
- Relationship Identification Between Conversational Agents Using Emotion AnalysisCognitive Computation, 2021
- Recent Developments in the Treatment of DepressionBehavior Therapy, 2019
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989