課程大綱

深度學習

本課程之課程大綱如下:

  1. Applied Math and Machine Learning Basics
  2. Deep Feedforward Networks
  3. Regularization for Deep Learning
  4. Optimization for Training Deep Models
  5. Deep Learning Research

本課程之授課時程預定如下:(本課程已於105學年第二學期開課)

每週進度表
週次 上課日期 課程進度、內容、主題
1 2/17 Introduction to Deep Machine Learning
2 2/24 Probability, Information Theory & Numerical Computation
3 3/3 Deep Learning Applications
4 3/10 Deep Feedforward Networks
5 3/17 Regularization for Deep Learning
6 3/24 Approximate Inference
7 3/31 Variational Inference & Monte Carlo Methods
8 4/7 Optimization for Deep Models
9 4/14 Midterm Exam
10 4/21 Auto-Encoders
11 4/28 Stochastic Error Backpropagation Algorithm
12 5/5 Deep Generative Models
13 5/12 Deep Boltzmann Machines
14 5/19 Generative Stochastic Networks
15 5/26 Convolutional Neural Networks
16 6/2 Recurrent Neural Networks
17 6/9 Gated Recurrent Neural Networks
18 6/16 Final Exam & Project Presentation

 

評量方式

Midterm Exam (25%)、Final Exam (35%)、Homework (20%)、Final Project (20%)、Class Attendance (+10%)