I’m proud to share our latest paper published in the Journal of the Experimental Analysis of Behavior (JEAB).
This publication holds a special meaning for me, not only because of JEAB’s historical and foundational role in our field, but also because it marks two personal milestones: 20 years since I began my journey as a student in behavioral science, and 10 years as a researcher at Universidad Veracruzana.
This work is the result of a committed and talented team whose dedication, enthusiasm, and discipline have produced high-quality data and innovative methods. These efforts have led to exciting collaborations with institutions such as the University of Montreal and outstanding researchers like Marc Lanovaz.
I feel deeply grateful for the path that brought us here and more committed than ever to expanding the scope and impact of behavioral science.
In this paper, we present three main contributions:
-
The implementation of machine learning algorithms to predict which reinforcement schedule the organism is exposed to.
-
Empirical evidence of the sensitivity of spatiotemporal behavioral features to the contingencies.
-
A novel approach to programming reinforcement schedules based on spatiotemporal variability.
Overall, our study demonstrates that machine learning algorithms can accurately detect the presence or absence of programmed reinforcement and distinguish between fixed- and variable-space schedules in rats.
🐀🔍📈
Read the full article here:
Machine learning to detect schedules using spatiotempor al data of behavior: A proof of concept
Marc J. Lanovaz, Varsovia Hernández, Alejandro León
First published: June 30, 2025
https://doi.org/10.1002/jeab.70029
