Computer Science - UG3/G
Course Deep Learning I
Term 2023F
Final Tba
Credits 3
Staff WU Xiaokun 吴晓堃
Lecture 48 hours (12 weeks)
计算机科学专业选修课
人工智能专业核心课
课程名称 深度学习I
授课时间 2023年春
考试形式 考试/考查
学分 3
讲者 吴晓堃
总计时长 48学时(12周)

Course Information

Short Intro

The objective of this course is to provide a complete introduction to deep machine learning. General artificial intelligence and machine learning techniques will be quickly reviewed in a historical connections fashion, but the focus of this course is machine learning. So the main theme here is to understand modern techniques that specifically handle deep neural network: how to design it, how to train it and how to evaluate it on real problems.

Description

The course aims at providing an overview of existing approaches and methods, at teaching how to design and train a deep neural network for a given task, and (depending on the audience,) at providing the theoretical basis to go beyond the topics directly seen in the course.

The course will touch on the following topics:

Concepts will be illustrated with examples in the PyTorch framework.

Keywords: deep learning, neural networks, python, PyTorch

Course group

Previous offers: [2022]

Closely related: [Artificial Intelligence], [Machine Learning], [Natural Language Processing]

Prerequisites

We expect you to have the following skills before taking this course:

本课程建议掌握如下专业知识:

Required

Recommended

Teaching Plan

This course is organized into a 12-week session (4 hours per week). The main contents are listed below:

本课程计划安排12周内容,主要讲授内容分别如下:

  1. Introduction 导言:什么是深度学习
  2. Preliminaries 预备知识
  3. Linear Neural Networks 线性神经网络
  4. Multilayer Perceptrons 多层感知机
  5. Deep Learning Computation 深度学习计算
  6. Convolutional Neural Networks 卷积神经网络
  7. Modern Convolutional Neural Networks 现代卷积神经网络
  8. Computer Vision: Applications I 计算机视觉应用I
  9. Computer Vision: Applications II 计算机视觉应用II
  10. Recurrent Neural Networks 循环神经网络
  11. Modern Recurrent Neural Networks 现代循环神经网络
  12. Natural Language Processing: Applications I 自然语言处理应用I

For classes that also take Natural Language Processing 2023F, NLP part will be changed as follows:

对于同时学修《自然语言处理》的班级,课程关于NLP的部分将调整为如下内容:

  1. Attention Mechanisms 注意力机制
  2. Transformers and Pretraining Transformers及预训练
  3. Natural Language Processing: Applications II 自然语言处理应用II

Schedule

Multiple offerings; Multiple locations.

Week Date Lecture Handouts
1 2023/02/27 [导言] [课程信息]
2 2023/03/06 [预备知识] [安装]
3 2023/03/13 [线性回归]
4 2023/03/20 [线性分类]
5 2023/03/27 [前馈神经网络]
6 2023/04/03 [深度计算]
7 2023/04/10 [卷积神经网络]
8 2023/04/17 [现代卷积神经网络]
9 2023/04/24 [循环神经网络]
10 2023/05/01 holiday
11 2023/05/08 [现代循环神经网络]
12 2023/05/15 review

Methodology

Problem-solving oriented, equal emphasis on lecture and practice.

以解决实际问题为导向,教学与实践并重。

Each lecture is roughly organized into 3 progressive units:

  1. Core Concepts 核心概念: provides elementary knowledge of the topic
  2. Advanced Discussion 进阶讨论: provides in-depth understanding, mathematical formulations
  3. Practical Skills 实践技巧: provides problem-solving skills through hands-on programming training

Evaluation

Textbook

Not mandatory but recommended:

以《动手学深度学习》为主。其他辅助教材:

Resource


  1. https://zh-v2.d2l.ai↩︎

  2. https://speech.ee.ntu.edu.tw/~hylee/ml/2022-spring.php↩︎