Dr. Alexander Mathis, Postdoctoral Fellow, Harvard University
Quantifying behavior is crucial for many applications across the life sciences and engineering. Videography provides easy methods for the observation and recording of animal behavior in diverse settings, yet extracting particular aspects of a behavior for further analysis can be highly time consuming and computationally challenging. I will present an efficient method for markerless pose estimation based on transfer learning with deep neural networks that achieves excellent results with minimal training data. I will demonstrate the versatility of this framework by tracking various body parts in multiple species across a broad collection of behaviors from egg-laying fruits flies to hunting cheetahs. Moreover, I will show that for both pretrained and networks trained from random initializations, better ImageNet-performing architectures perform better for pose estimation, with a substantial improvement on out-of-domain data when pretrained on ImageNet.
Alexander Mathis is a postdoctoral fellow working with Prof. Venkatesh N. Murthy at the Department of Molecular and Cellular Biology (Harvard). He is interested in elucidating how the brain gives rise to adaptive behavior with a particular interest in olfactory and motor behaviors. For those purposes, he develops deep learning methods to analyze animal behavior, neural data, as well as creates experimentally testable computational models. His PhD thesis supervised by Prof. Andreas Herz focused on deriving properties of grid cells from optimal coding assumptions.