Teaching Machine Learning with Cockroaches
Author Information
Author(s): Truong Vincent, Moore Johnathan E., Ricoy Ulises M., Verpeut Jessica L.
Primary Institution: Arizona State University
Hypothesis
Can a low-cost educational program using cockroaches and machine learning improve neuroscience education in underserved communities?
Conclusion
The study demonstrates that a low-cost educational program using machine learning can effectively teach neuroscience concepts and improve students' understanding of animal behavior.
Supporting Evidence
- SLEAP was within a 0.5% margin of error compared to manual scoring.
- Participants reported a 94% increase in behavior tracking knowledge after using SLEAP.
- Over half of the participants incorporated SLEAP into their research.
Takeaway
This study shows that students can learn about animal behavior and machine learning using cockroaches without needing expensive equipment.
Methodology
Cockroaches were trained to explore a linear track while exposed to different conditions, and their behavior was analyzed using the SLEAP machine learning software.
Potential Biases
Potential biases in self-reported data from participants regarding their learning outcomes.
Limitations
The study may not generalize to other species or settings outside of the educational context.
Participant Demographics
Participants included K-12 and college undergraduate students, particularly from underserved communities.
Statistical Information
P-Value
p<0.001
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website