DeepLabCut-Live allows for real-time, ultra-low latency posture tracking of animals.

A deep neural network trained on semi-synthetic data learns to quickly track and identify neurons in Caenorhabditis elegans.

Many disorders are characterized by underlying abnormalities in network connectivity which, though difficult to address with explicit training procedures, can be directly targeted through covert neurofeedback.

The ability to follow single objects in 3D in a living organism with high spatiotemporal resolution opens new possibilities for quantitative biophysical studies of complex systems in their physiological context.

A statistically principled approach developed to estimate phase of rhythmic signals in real-time shows robustness to multiple sources of error and also provides confidence criteria.

Seasonal selection is a general feature of Drosophila melanogaster genetic variation, occurring in North American and European populations and affecting large proportions of the genome.

Being fast, memory efficient, easy to use, and with powerful integrated tools, TRex will lower barriers of entry into, and enable more ambitious approaches to, the quantitative study of behavior.

A novel high-throughput FPGA-based multi-animal tracking and training system was used to demonstrate trace and operant conditioning in Drosophila larvae.

Using novel approach to study real-time social interactions shows that mutual action visibility facilitates static and dynamic coordination in both species, but whereas humans employ dynamic turn-taking to equalize rewards, macaques, after training with a human, compete between themselves.

The integration of a novel high spatiotemporal resolution volume imaging technique and a fast 3D tracking system allows capturing whole brain neural activities in a freely behaving larval zebrafish.