Recent advances in information technology makes it possible to collect and store large quantities of healthcare data including electronic health records, images (such as CT scans, PETs, Ultrasounds, etc.), data collected from sensors and other pervasive devices, genomic data and more. Understanding this data and extracting knowledge from it requires development of advanced analytical techniques that can transform data into meaningful, actionable information. This course will introduce different modalities of healthcare data, machine learning pipelines (including data cleaning and processing, techniques for supervised and unsupervised learning along with evaluation metrics), use of natural language processing for understanding clinical text (such as vector representation of documents, embeddings, topic modeling, etc.), image understanding and analysis, and use of advanced analytical techniques such as deep learning (Multilayer Perceptrons (MLPs), Convolutional and Recurrent Neural Networks) and generative AI (Autoencoders, Attention Models, Graph Neural Networks and Generative Adversarial Networks) to process healthcare data. Students will work on individual projects to gain hands-on experience in designing, implementing, and debugging analytical pipelines for processing healthcare data. Evaluation will be based on quizzes and a project comprising of two parts. Prior knowledge of programming and statistics are highly recommended.