Introduction to Machine Learning

Course Information

  • Instructor: Yifeng Tao
  • Time: Mon-Fri 9:50-11:30AM / 9:50-12:00PM, May 13-24 2019
  • Location: Institute of Industrial and Systems Engineering, Northeastern University

    Course Description

    The recent advancement of machine learning, especially the development of deep learning, has essentially influenced the area of computer vision, natural language processing, and computational biology. In this series of lectures and seminars of "Introduction to Machine Learning", I will introduce the general knowledge of machine learning, such as supervised learning, unsupervised learning, deep learning, as well as specific topics of machine learning application in precision medicine and clinical text mining.

    Syllabus

    Date Lecture Topics Slides
    Mon, May 13 Lecture 1 Supervised learning: linear models [Link]
    Tue, May 14 Lecture 2 Kernel machines: SVMs and duality [Link]
    Wed, May 15 Lecture 3 Unsupervised learning: latent space analysis and clustering [Link]
    Thu, May 16 Lecture 4 Decision tree, kNN and model selection [Link]
    Fri, May 17 Lecture 5 Learning theory: generalization and VC dimension [Link]
    Mon, May 20 Lecture 6 Neural network (basics) [Link]
    Tue, May 21 Lecture 7 Deep learning in computer vision and natural language processing [Link]
    Wed, May 22 Lecture 8 Probabilistic graphical models [Link]
    Thu, May 23 Lecture 9 Attention mechanism and transfer learning in precision medicine [Link1, Link2, Link3]
    Fri, May 24 Lecture 10 Reinforcement learning and its application in clinical text mining [Link]

    References

    This course mainly reuses and is based on the materials from the following courses: 10601 Introduction to Machine Learning by Matt Gormley, 10701 Introduction to Machine Learning by Eric Xing and Tom Mitchell, 10701 Introduction to Machine Learning by Eric Xing and Ziv Bar-Joseph, 10715 Advanced Introduction to Machine Learning by Barnabas Poczos, 10725 Convex Optimization by Ryan Tibshirani. It also reuses materials from the Book: Christopher M. Bishop. Pattern Recognition and Machine Learning. Feel free to reuse these materials for educational purpose. Please retain any copyright notices, and include written notice indicating the source of any materials you use.