Kristin Branson develops machine vision and learning algorithms designed to extract scientific understanding from imaging and video data sets resulting from large-scale, neurological studies of behaving animals. Branson and her team use these high-throughput tools to address previously unanswerable questions about the brain and behavior, thereby gaining insight into nervous system function, evolution, and ethology. Their goal is to develop robust, general-purpose implementations of these algorithms that are freely available for widespread use by biologists worldwide.
Scientists at HHMI’s Janelia Research Campus created comprehensive brain maps linking different groups of neurons to specific behaviors, using a machine-learning program that annotated more than 225 days of videos of flies – a feat that would have taken humans some 3,800 years. New experiments at HHMI’s Janelia Research Campus show that activity in the cortex is critical for enacting a learned skill. Janelia researchers develop a new computational method that can essentially automate much of the time-consuming process of reconstructing an animal’s developmental building plan cell by cell. Rather than scrutinizing hours of video, scientists can quickly teach the software how to recognize key behaviors. Over the past year, two scientists who have been at Janelia since its opening took on new roles as group leaders, and six new fellows were recruited to head their own research groups.