Home

This course introduces algorithms, tools, practices, and applications of machine learning. Topics include core methods such as supervised learning (classification and regression), unsupervised learning (clustering, principal component analysis), Bayesian estimation, neural networks; common practices in data pre-processing, hyper-parameter tuning, and model evaluation; tools/libraries/APIs such as scikit-learn, Theano/Keras, and multi/many-core CPU/GPU programming.

Table of Contents Information (autumn semester 2016) Prerequisite Grading Reading Schedule

Information (autumn semester 2016)

Time

• Tue 16:30-18:20
• Fri 17:30-18:20

Place

• CBA

Mediums

• Moodle

Tutor (i.e. the real boss who grades your stuff)

• Mengqi PENG

Prof

• Li-Yi WEI

For faster response, please use the Moodle discussion board for general questions, and email us (c3314 at cs.hku.hk) only for personal matters.

Prerequisite

I personally would not enforce prerequisites, and believe the best way to judge whether you are ready to take this course is to look at the materials, in particular the first assignment, which will be available within the first week of the semester to facilitate add/drop.

• Math
  • calculus
  • linear algebra
  • probability
  • optimization
• Coding
  • python
• Tools
  • anaconda
    • scikit-learn
    • ipynb
  • git

Grading

• Assignments (50%)
  • all digital via ipynb to put everything (text, math, code, data, image, etc.) in one place
• Final exam (50%)

Reading

• Python Machine Learning, by Sebastian Raschka
  • basic ideas and code
• Introduction to Machine Learning, by Ethem Alpaydin
  • more math and theory
• Pattern Recognition and Machine Learning, by Christopher Bishop
  • further reference
• More beyond the basic stuff covered in the semester

Schedule

• CS timetable 2016 Autumn