Low-Cost Approaches in Neuroscience to Teach Machine Learning Using a Cockroach Model
2024

Teaching Machine Learning with Cockroaches

Sample size: 18 publication 10 minutes Evidence: moderate

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)

10.1523/ENEURO.0173-24.2024

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication