進階機器學習

``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, deep learning has been applied to many real world problems successfully. We will introduce the important and well known neural networks such as the convolutional neural networks, CNN for image classification and recognition, the recurrent neural networks, RNN for sequential data. Representation learning and deep reinforcement learning will be included as well. Also some special topics and applications will be discussed.

Machine Learning Mathematical analysis Numerical Methods Linear Algebra Probability

無備註

教師未提供此項資料

Homework: 30% Presentation in the class: 40 % Final Project: A Kaggle Competition, 30 %

教師未提供此項資料

Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep learning. The MIT Press, 2016.

地點

SA-240

時間

Making the appointment by e-mail

聯絡方式

yuhjye@math.nctu.edu.tw