深度學習

Deep learning is a branch of machine learning and recently receive a lot of attention due to its state-of-the art performance. Deep learning has been applied extensively to many areas such as computer vision, speech recognition, natural language processing, bioinformatics, and wireless networks. In this course, we will introduce various deep learning architectures and techniques, and discuss the advances in this area through paper presentation (by students). Students have the chance to practice implementing deep learning by doing programming homework and applying deep learning to real problems by doing final project.

Probability, linear algebra, machine learning (preferred but not required)

無備註

教師未提供此項資料

Homework (programming using Python): 30% Paper presentation + debate: 15% Midterm exam: 30% Final project: 25%

• Introduction to machine learning
• Deep feedforward networks
• Regularization for deep learning
• Optimization for training deep models
• Convolutional networks
• Recurrent and recursive networks
• Autoencoders
• Monte Carlo methods
• Deep generative models
• Reinforcement learning

1. I. Goodfellow and Y. Bengio and A. Courville, Deep Learning, The MIT Press, 2016 2. (For machine learning basics) C. Bishop, Pattern Recognition and Machine Learning, Springer, 2007

地點

ED808

時間

By appointment

聯絡方式

chiahan@nctu.edu.tw