Topic outline

  • General

    Check Section "Course Schedule" for Course Activities!

    Teachers: Shamsi Abdurakhmanova  and Alexander Jung
     Teaching Assistant: Andi Ramos Sardina

    Response Letter to Student Feedback (What's New?)

    Deep learning methods use a simple principle: extrapolate from previous examples. These methods fit non-linear functions, represented by artificial neural networks, to massive amounts of data. Such non-linear functions might then be used to detect the presence of a face mask in a webcam snapshot (demo). The increasing availability of computation and data allows deep learning to achieve super-human performance within computer vision and natural language processing. 

    This course teaches you how to train deep neural networks on different kinds of data. Our focus will be on image data for which deep learning methods seem to be most matured. However, deep learning methods for images can be applied to other types of data ( natural language, audio signals, or even battery materials) as long as we can construct images (visualizations) of it. We will not focus on the details of particular learning algorithms but rather develop intuition and hands-on skills for applying deep learning using Python libraries. 

    The course material is in the form of Python notebooks that contain code snippets along with their explanations. These notebooks contain coding assignments and multiple-choice questions that students have to complete. Students can earn up to 100 points during the entire course.

    Course workload: 2 credits (54 hours of work); Grading is pass/fail. Pass requires at least 60 points.

    SLACK Discussion Forum: Course Slack can be joined by using this link.