Intended Audience for CS243


Who should take this course?

  • Students who want an introduction to practical methods in machine learning with an emphasis on techniques and algorithms popular in artificial intelligence.

  • Self-motivated students who are willing to put in the work needed to learn the necessary background in statistics, estimation and optimization. There will be few graded exercises and exams and there are several concepts that simply can't be learned without working through the examples and carefully pouring over the mathematics.


    Who should not take this course?

  • Anyone expecting a comprehensive, in-depth introduction to the underlying mathematical concepts including statistical inference, hypothesis testing, analysis of algorithms, estimation theory and optimization theory should look elsewhere. There are excellent courses offered in the Computer Science, Mathematics and Applied Mathematics Departments covering each of these areas.

    Note that the relevant mathematics for this course is "introductory" in the sense that it is generally taught in 100-level or lower courses. However, this material is drawn from several areas of mathematics and hence it is not covered in depth in any single course. For this course, it is expected that the math can be handled by a student with basic college calculus, some facility with boolean logic and symbolic manipulation, and a willingness to learn new concepts with a minimum of handholding.

  • Anyone who doesn't want to "get their hands dirty" writing code, gathering data, and running experiments and trying to make sense of the results. The grade for this course is based primarily on a project that requires students to implement learning algorithms, test them on real problems and analyze the results using appropriate methods from statistics.