(AD1062) Machine Learning Fundamentals
2018 R1 History Archive
Course Introduction
Machine Learning Fundamental is a Trend Micro ETP course which expected to provide you the background knowledge of popular machine learning methods. Started from the simplest linear classifier, Perceptron, we'll introduce how a classifier learning from large volumes of data via different strategies and obtaining the ability to predict the properties of data. The course also provides an overview for different purposes of learning. For example, using Convolutional Neural Network (CNN) for visual information extraction, using Recurrent Neural Network (RNN) to handle context-dependent information, or using Generative Adversarial Network (GAN) to synthesize structured information.
Notice that we do NOT cover too much about:
- How to develop a machine learning application (Only basic sample code would be provided)
- How to choose and use machine learning framework
- How to handle your data., etc.
The course materials only covers:
- Understanding the basic concept of some widely used machine learning algorithms,
- The applicable and non-applicable scenario for different methods, and
- The physical meanings of parameters for particular algorithm that you usually read from Scikit-learn or TensorFlow tutorial
Schedule
Announcement
- The last homework submission deadline: 2018/5/6 (Sun.) - Please try your best to submit your homework before this date
- If you're satisfied/unsatisfied with the course this time, please help me to fill-in the [questionnaire] (課程問卷,中文)
Thank you for your participation! :)
2018/3/7
Overview
Course Materials: [PowerPoint slides] [PDF] - Update: 2018/3/7
Sample code: [demo_01]
Homework: [Link of Homework 1] - Deadline: 2018/3/14 (Soft deadline, please notify me for late submission )
- Overview
- Data Preparation
- Mathematics Review: Linear Algebra - Part.1
- Vectors, Matrices and its operators
- Norms
- Reference: Linear Algebra Review and References (From CS229: Machine Learning, Stanford): http://cs229.stanford.edu/section/cs229-linalg.pdf
- Performance Evaluation
2018/3/14
Linear Classifier
Course Materials: [PowerPoint slides] [PDF] - Update: 2018/3/14
Sample code: [demo_02] - NOTICE: Please clone the whole tu-etp-1062 github if you need to execute it!
Homework: [Link of Homework 2] - Deadline: 2018/3/28 (Soft deadline, please notify me for late submission)
- Mathematics Review: Linear Algebra - Part.2.
- Hyper-plane and Normal Vector
- Perceptron
- Reference: the Matrix Cook book (if you need to derive your own cost function with gradient descent): http://www2.imm.dtu.dk/pubdb/views/edoc_download.php/3274/pdf/imm3274.pdf
- Support Vector Machine (SVM)
2018/3/28
Linear Classifier
- Multi-Class Generalization
Non-Linear Classifier
Course Materials: [PowerPoint slides][PDF] - Update: 2018/3/27
Sample code: [demo_03]
Homework: [Link of Homework 3] - Deadline: 2018/4/11 (Soft deadline, please notify me for late submission)
- Multi-Layer Perceptron
- Non-linear Support Vector Machine
2018/4/11
Non-Linear Classifier
- Decision Tree and Boosting
Selected Topics on Deep Neural Network I: Convolutional Neural Network
Course Materials: [PowerPoint slides][PDF] - Update 2018/4/18
Sample code & Homework material: [demo04_homework]
Homework: [Link of Homework 4] - Deadline: 2018/4/25 (Soft deadline, please notify me for late submission)
- Convolution mask
- Convolutional Neural Network
- Convolutional Layer
- Pooling Layer
- Fully-connected Layer
- Drop-out Layer
- Activation Layer
2018/4/18
Selected Topics on Deep Neural Network I: Convolutional Neural Network
- Applications
- Image Classification
- Object Detection and Localization
Selected Topics on Deep Neural Network II: Context-Dependent Learning
Course Materials: [PowerPoint slides][PDF] - Update 2018/4/18
Sample code & Homework material: [demo05_homework]
Homework: [Link of Homework 5] - Deadline: 2018/5/6 (HARD DEADLINE!)
- N-gram model and Markov-Chain
- Recurrent Neural Network (RNN)
- Long Short-Term Memory (LSTM)
- Applications
Notice: GAN is temporary removed due to the schedule concerns.
2018/4/25
Dimension Reduction
Course Materials: [PowerPoint slides][PDF] - Update 2018/4/25
Sample code: [demo_06]
- Principal Component Analysis (PCA)
- Linear Discriminant Analysis (LDA)
- t-Distributed Stochastic Neighboring Embedding (t-SNE)
Summary
Course Materials: [PowerPoint slides][PDF] - Update 2018/4/25
About the Lecturer
Jessee Kung
Sr. Developer at Trend Micro Inc.
jessee780522 {at} gmail.com