This course covers a wide range of introductory topics to machine learning, data mining, and statistical pattern recognition. Topics include different supervised and unsupervised learning methods, parameter estimation techniques, learning theory: bias-variance trade-off, and automatic complexity control such as regularization, deep learning, and different types of advanced learning such as imitation, transfer, and semi-supervised. Students learn about effective machine learning techniques and gain practice in implementing them.

Further information: Course availability and times