Learning with Limited Labels - ODSC West 2020

The course focuses on learning with limited labels, introducing research on domain adaptation, low-shot learning, and self-supervised learning algorithms to transfer information across domains and recognize novel categories with few-shot samples. The course covers topics such as adversarial multiple source domain adaptation, compositional few-shot recognition, and generalized zero-shot learning. The teaching method includes lectures on various algorithms and techniques related to handling limited labeled data. The course is intended for individuals interested in machine learning, deep learning, and domain adaptation techniques.