Using generative and explainable neural networks to investigate the relationship between motor cortex activity and animal behavior during skilled reach learning

Understanding complex relations between neuronal activity and animal behavior is one of the most crucial questions in neuroscience. Rapid advancements in Machine Learning (ML) methods offer new powerful tools that can be used to investigate highly non-linear mapping between motor cortex activity and body movements. Here, by using explainable convolutional network (ConvNet) and Generative Adversarial Networks (GAN), we show how neuronal activity can be predicted from raw videos of animal behavior, and interestingly, we show that detailed videos of behaving animals can be recreated from activity of just few selected neurons. Those analyses revealed that the predictability of behavior from neuronal activity (and vice versa) initially increases as an animal learns a new task. However, after the animal performance on a motor task achieves the required accuracy, then “coupling” between neuronal activity and behavior decreases, without degrading task performance. In summary, we aimed to improve the understanding of skilled reach learning by moving past the need for predefined limb markers. By using advanced, data-driven machine learning, we were able to recreate behavioral videos from neural activity and predict neuronal firing patterns from raw videos, providing new insights into the complex processes involved in skilled reach behavior. To provide all the details about our models and analyses we posted our code with documentation at: https://github.com/seantanabe/GAN_ConvNet_rat_reach_motor_cortex. There are also included original and generated videos and neuronal data.

Authors

• Tanabe, Sean
• University of Lethbridge. Faculty of Arts and Science

• Behavior
• Motor cortex
• Convolutional neural networks
• Generative Adversarial Networks
• Explainable AI
• Neuronal activity
• Skilled reach behavior

Identifier

hdl:10133/6925

OAI identifier oai:identifier

oai:opus.uleth.ca:10133/6925