In this course, students will learn machine learning techniques to analyze text, image, video, and audio data. The course consists of three parts: general techniques, image/video analysis and audio analysis. Each part will first introduce how these non-traditional data can be converted into mathematical objects suitable for computer processing and, particularly, for the application of machine learning techniques. Students will then learn a selection of supervised, unsupervised, and deep learning algorithms that are effective for text, image/video and audio analysis. Finally, the course will introduce major applications of these techniques such as object detection, face recognition, image classification, speaker detection, speech recognition, etc. The course also provides opportunities to apply machine learning techniques to the Wesleyan Media Project data sets.