Both mice and rats are used frequently for scientific research, but currently scientists must use ambiguous physical cues - such as a rodent pressing a lever to receive a dose of an addictive substance - or time-consuming manual methods of analysing rodent chatter to try to understand what drives their behaviour during trials.
But now, a new project from the University of Washington aims to better decipher the squeaks and chirps of mice and rats, by using deep learning to more quickly and reliably analyse their chatter, helping researchers to understand what they're really saying.
The new technology is called DeepSqueak, and it uses deep learning and machine vision approaches to categorise the enigmatic chirps of mice and rats, by transforming audio recordings of rodent calls into sonogram images and using machine vision to analyse them.
Kevin Coffey, co-creator of the software, said in a paper describing the project, which was published in the journal Neuropsychopharmacology: "We can train the software to analyse these calls in a way that is much more similar to how humans learn. Rather than mathematically describing what a vocalisation is, we just show it pictures and examples."
Researchers believe DeepSqueak will help them develop a better understanding of rodent behaviour and motivation, which can then be applied for human treatments as well.
Kevin added: "[For example] in drug addiction we need to know not just if the animal is taking drugs but why are they taking the drugs. Are they taking the drugs because they like it or because they're escaping the negative feelings associated with withdrawal?"
Developers of DeepSqueak also hope the technology will help them research animal models of depression, anxiety, and even Parkinson's disease.