機器學習

"Google's always used machine learning. In all the areas we applied it to, speech recognition, then image understanding, and eventually language understanding, we saw tremendous improvements." John Giannandrea, then VP of Engineering, Google In the last decade, machine learning has been applied to many real world problems successfully. It is considered as the most essential and fundmental knowledge for a data scientist. We introduce core concept of machine learning and several useful learning methods including linear models, nonlinear models, kernel methods, dimension reduction, unsupervised learning (Clustering) and deep learning. Also some special topics and applications will be discussed.

 Mathematical analysis  Numerical Methods  Linear Algebra  Probability  Programming skills

Homework: 30% Final Exam: 40% Final Project: A Kaggle Competition, 30%

Deep Learning, Ian Goodfellow, Yoshua Bengio and Aaron Courville, 2016

地點

SA-240

聯絡方式

yuhjye@math.nctu.edu.tw 5131427