Learning to Walk
Legged locomotion is commonly studied and programmed as a discrete set of structured gait patterns, like walk, trot, gallop. However, studies of children learning to walk (Adolph et al) show that real-world locomotion is often…
Legged locomotion is commonly studied and programmed as a discrete set of structured gait patterns, like walk, trot, gallop. However, studies of children learning to walk (Adolph et al) show that real-world locomotion is often…
Our work in machine learning theory ranges from modeling to mathematical analysis of algorithms to experimental probing. The diverse set of topics include clustering, optimization, unsupervised learning, algebraic methods, fairness, causality, and deep learning.
xtreme classification is a rapidly growing research area in computer vision focusing on multi-class and multi-label problems involving an extremely large number of labels (ranging from thousands to billions).