Data Augmentation for Automated Adaptive Rodent Training
This work addresses the problem of automating rodent training for researchers, but it appears incremental as it builds on existing data augmentation techniques.
The researchers tackled the labor-intensive process of rodent behavioral training by using data augmentation to build artificial rodent models and a novel similarity metric to measure their behavioral resemblance to real rodents, resulting in an efficient and automatic trainer.
Fully optimized automation of behavioral training protocols for lab animals like rodents has long been a coveted goal for researchers. It is an otherwise labor-intensive and time-consuming process that demands close interaction between the animal and the researcher. In this work, we used a data-driven approach to optimize the way rodents are trained in labs. In pursuit of our goal, we looked at data augmentation, a technique that scales well in data-poor environments. Using data augmentation, we built several artificial rodent models, which in turn would be used to build an efficient and automatic trainer. Then we developed a novel similarity metric based on the action probability distribution to measure the behavioral resemblance of our models to that of real rodents.