CS565600 Deep Learning

Fundamentals of machine learning, deep learning, and AI.

Description

This class introduces the concepts and practices of deep learning. The course consists of three parts. In the first part, we give a quick introduction of classical machine learning and review some key concepts required to understand deep learning. In the second part, we discuss how deep learning differs from classical machine learning and explain why it is effective in dealing with complex problems such as the image and natural language processing. Various CNN and RNN models will be covered. In the third part, we introduce the deep reinforcement learning and its applications.

This course also gives coding labs. We will use Python 3 as the main programming language throughout the course. Some popular machine learning libraries such as Scikit-learn and Tensorflow will be used and explained in detials.

Syllabus (Tentative)

Instructor

Teaching Assistants

Time & Location

  • Tue. 3:30-5:20pm at Delta 107
  • Thu. 3:30-4:20pm at Delta 107
  • Office hour: Wed. 3-5pm at Delta 723/724

Grading Policy

  • Competitions (x5): 60%
  • Lab Quiz: 40%

Prerequisites

This course is intended for senior undergraduate and junior graduate students who understand

  • Computer Programming (Python),
  • Calculus,
  • Linear Algebra, and
  • Probability.
Although not required, background knowledge about scientific computing and classic machine learning will be helpful.

Announcement

Curriculum

If you have any feedback, feel free to contact: shwu [AT] cs.nthu.edu.tw

Lecture 01

Introduction

What's ML? | How DL Differs from Classic ML? | About This Courses | FAQ

Slides Notation

Scientific Python 101

This lab guides you through the setup of scientific Python environment and provides useful references for self-reading.

Notebook

Lecture 02

Linear Algebra

Span & Linear Dependence | Norms | Eigendecomposition | Singular Value Decomposition | Traces | Determinant

Video Slides

Data Exploration & PCA

This lab guides you through the process of Exploratory Data Analysis (EDA) and discuss how you can leverage the Principle Component Analysis (PCA) to visualize and understand high-dimensional data.

Notebook

Lecture 03

Probability & Information Theory

Random Variables & Probability Distributions | Multivariate & Derived Random Variables | Bayes’ Rule & Statistics | Principal Components Analysis | Information Theory | Decision Trees & Random Forest

Video Slides

Decision Trees & Random Forest

In this lab, we will apply the Decision Tree and Random Forest algorithms to the classification and dimension reduction problems using the Wine dataset.

Notebook

Lecture 04

Numerical Optimization

Numerical Computation | Optimization Problems | Unconstrained Optimization | Stochastic Gradient Descent | Perceptron | Adaline | Constrained Optimization | Linear & Polynomial Regression | Duality

Video Slides

Perceptron & Adaline

In this lab, we will guide you through the implementation of Perceptron and Adaline, two of the first machine learning algorithms for the classification problem. We will also discuss how to train these models using the optimization techniques.

Notebook

Regression

This lab guides you through the linear and polynomial regression using the Housing dataset. We will also extend the Decision Tree and Random Forest classifiers to solve the regression problem.

Notebook

Lecture 05

Learning Theory & Regularization

Point Estimation | Bias & Variance | Consistency | Decomposing Generalization Error | Weight Decay | Validation

Video Slides

Regularization

In this lab, we will guide you through some common regularization techniques such as weight decay, sparse weight, and validation.

Notebook

Lecture 06

Probabilistic Models

Maximum Likelihood Estimation | Maximum A Posteriori Estimation | Bayesian Estimation

Video Slides

Logistic Regression & Metrics

In this lab, we will guide you through the practice of Logistic Regression. We will also introduce some common evaluation metrics other than the "accuracy" that we have been used so far.

Notebook

Lecture 07

Non-Parametric Methods & SVMs

KNNs | Parzen Windows | Local Models | Support Vector Classification (SVC) | Nonlinear SVC | Kernel Trick

Video Slides

SVMs & Scikit-Learn Pipelines

In this lab, we will classify nonlinearly separable data using the KNN and SVM classifiers. We will show how to pack multiple data preprocessing steps into a single Pipeline in Scikit-learn to simplify the training workflow.

Notebook

Lecture 08

Cross Validation & Ensembling

CV | How Many Folds? | Voting | Bagging | Boosting | Why AdaBoost Works?

Video Slides

CV & Ensembling

In this lab, we will guide you through the cross validation technique for hyperparameter selection. We will also practice and compare some ensemble learning techniques.

Notebook

Competition 01

Predicting Appropriate Response

In this competition, you have to select the most appropriate response from 6 candidates based on previous chat message. Your goal is to learn a function that is able to predict the best response.

Notebook

Lecture 09

Large-Scale Machine Learning

When ML Meets Big Data... | Representation Learning | Curse of Dimensionality | Trade-Offs in Large-Scale Learning | SGD-Based Optimization

Video Slides

Lecture 10

Neural Networks: Design

NN Basics | Learning the XOR | Back Propagation | Cost Function & Output Neurons | Hidden Neurons | Architecture Design

Video Slides

TensorFlow101 & Word2Vec

In this lab, we will introduce basic concepts of TensorFlow. Then we train a neural network, called the word2vec, that embeds words into a dense vector space where semantically similar words are mapped to nearby points.

Notebook

Lecture 11

Neural Networks: Optimization & Regularization

Momentum & Nesterov Momentum | AdaGrad & RMSProp | Batch Normalization | Continuation Methods & Curriculum Learning | Weight Decay | Data Augmentation | Dropout | Manifold Regularization | Domain-Specific Model Design

Video Slides

Lecture 12

Convolutional Neural Networks

Convolution Layers | Pooling Layers | Variants & Case Studies | Visualizing Activations | Visualizing Filters/Kernels | Visualizing Gradients | Dreaming and Style Transfer | Segmentation and Localization | Object Detection | More Applications

Video Slides

Nuts and Bolts of Convolutional Neural Networks

In this lab, we will introduce two datasets, MNIST and CIFAR-10, then we will talk about how to implement CNN models for these two datasets using tensorflow. Then offer a guide to illustrate typical input pipeline of TensorFlow.

Notebook

Visualization and Style Transfer

This lab guides how to load and use a pretrained VGG19 model and how to visualize what the CNN network represents in selected layers. This also introduces an interesting technique called "Style Transfer" and displays galleries of its creative outputs.

Notebook

Competition 02

Image Object Detection & Localization

In this competition, you should design a model to detect multiple objects in images. This is a multi-tasks problem, the first one is localization and second is classification.

Notebook

Lecture 13

Recurrent Neural Networks

Vanilla RNNs | Design Alternatives | Backprop through Time (BPTT) | LSTM | Parallelism & Teacher Forcing | Attention | Explicit Memory | Adaptive Computation Time (ACT) | Memory Networks | Google Neural Machine Translation

Video Slides

Seq2Seq Learning for Machine Translation

This lab guides how to use recurrent neural networks to model continuous sequence like nature language, and use it on not only article comprehension but also word generation.

Notebook

Competition 03

Image Caption

In this competition, you should design a model that can be given an image, then generates suitable caption which can describe the image.

Notebook

Lecture 14

Unsupervised Learning

Clustering | Factorization & Dimension Reduction | Manifold Learning & Data Synthesis | Predictive Learning | Autoencoders | Generative Adversarial Networks (GANs)

Video Slides

Autoencoders

In this lab, we are going to introduce Autoencoder. We will use MNIST dataset to show you how to use autoencoder to learn manifold.

Notebook

GANs

In this lab, we are going to introduce Generative Adversarial Networks. We will use MNIST dataset to show you how to use GAN to generate images.

Notebook

Competition 04

Reverse Image Caption

In this competition, given a set of texts, your task is to generate suitable imagese to illustrate each of the texts. We will guide you to use GANs to complete this competition.

Notebook

Lecture 15

Semisupervised/Transfer Learning and the Future

Label Propagation | Semisupervised GANs | Semisupervised Clustering | Multitask Learning | Weight Initiation & Fine-Tuning | Domain Adaptation | Zero Shot Learning | Unsupervised Transfer Learning | Future at a Glance

Slides

Lecture 16

Reinforcement Learning

Markov Decision Process(MDP) | Model-Free RL using Monte Carlo Estimation | Temporal-Difference Estimation and SARSA | Exploration Strategies | Q-Learning

Video Slides

Q-learning

In this lab, we will introduce temporal-difference learning and then use Q-learning to train an agent to play "Flappy Bird" game

Notebook

Lecture 17

Deep Reinforcement Learning

Introduction | DQN | Double DQN | Prioritized Reply | Dueling Network | NoisyNet and Scalable Implementations | Policy Gradient Methods & DDPG | Episodic Policy Gradient & REINFORCE | Reducing Variance | Baseline Subtraction | Function Approximation, Actor-Critic, and A3C

Video Slides

DQN & Policy Network

In this lab, we will introduce DQN and policy network and use them to train an agent to play "Flappy Bird" game

Notebook

Resources

Following provides links to some useful online resources. If this course starts your ML journey, don't stop here. Enroll yourself in advanced courses (shown below) to learn more.

Other Course Materials

For more course materials (such as assignments, score sheets, etc.) and online forum please refer to the iLMS system.

iLMS System

Reference Books

  • Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016, ISBN: 0387848576

  • Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition, Springer, 2009, ISBN: 0387848576

  • Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006, ISBN: 0387310738

  • Sebastian Raschka, Python Machine Learning, Packt Publishing, 2015, ISBN: 1783555130

Online Courses