Machine learning using MATLAB

This one-semester course provides a first introduction to machine learning including the following topics:

  • Linear regression
  • Logistic regression
  • Support vector machines
  • Deep Neural network
  • Dimensionality reduction
  • Clustering
  • Anomaly detection

complemented by a exercise session of practical Matlab exercises. 

Presentation schedule

Each group has 30 to 35 mins to present their project and 10 to 15 mins of Q&A. When you are doing your presentation, you may not finish your model training and performance evaluation, so you are allowed to present your motivation, framework of your approach, data collection, etc. 

No. Topic Member Time
1 Neural networks as universal approximator Maximilian Reihn

01.22

2

 Improving Decision Analytics with Machine Learning in stock markets Dang Mai, Michael Fischer

01.22
3 Star Classification using Neural Network Jorge Tapia Garcia 01.27
4 Image completing Mei Xie, Mohamed Aymane 01.27 
5 Human Step Recognition using smartphone sensor data Tobias Stähle, Philip Oesterlin, Fabian Seitz 01.29
6 Handwritten Text Recognition Orkhan Igidov, Sanani Rajabov, Muhammad Junaid Javed 01.29
7 Toxic comment classification Mariia Novik, Ahmet Melih Çelik, Mohnish Deshpande 02.03
8 Predicting Tennis Matches with Machine Learning Florina Curcă, Venkata Varun Kumar, Abhinav Mittal 02.03
9 Image enhancement using CycleGAN Guangan Chen 02.05
10 Predicting the Outbreak of War using Macroeconomic Data Jameson Hohbein, Mathew Smith 02.05
11 Brain Scan Image Classifier Masud Abdulkadir, Gawain Marti 02.10
12 Predicting the speed and movement direction of a vehicle Jonas Körner 02.10
13 Towards Machine Learning Comparisons based on Nutrition Classification Claudia Bartholt, Fabian Strauss 02.12
14 Identifying and Categorizing Offensive Language in Social Media Alisa Krstova 02.12

Note:

  • You can download lecture slides and assignments from uni gitlab.
  • Important dates:
    • Dec. 1st: submission of project title and group lists (up to 3 members in a group), note late submission will be rejected directly.
    • Dec. 18th: quiz in M630, please bring your laptop
    • Mar. 29th, submission of your report (up to 4 pages), note late submission will be rejected directly.
  • Report tempalte can download from here.

Prerequisites

None, if taken as a master course. If taken as an advanced course in the bachelor program:

  • basic math courses offered in our bachelor programs
  • algorithms and data structures
  • introduction to computer science including programming

Learning objective

You will

  • have an insight of the fundamentals of Machine Learning
  • have the ability to design your own machine learning algorithm to solve some specific problems with Matlab
  • know how to improve the performance using training data

Reference 

Textbook

  • Christopher M.. Bishop. Pattern recognition and machine learning. Springer, 2006.
  • Alpaydin, Ethem. Introduction to machine learning. MIT press, 2014.
  • Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep learning. MIT press, 2016