Course Syllabus

Jump to Today

Machine Learning DRAFT

 DIS Logo


vectorstock_20580328.png
  

Semester & Location:

Fall 2023 - DIS Stockholm
Type & Credits:

Core Course - 3 credits

Study Tours:

Sweden, Germany
Major Disciplines:

Computer science, Mathematics, Data Science

Prerequisite(s):

One year of computer science, a course in algorithms and data structures, one course in linear algebra at university level. A course in statistics is recommended. Knowledge of at least one programming language (e.g. Python/Javascript/Java/C++/Matlab).

Note: We will be using Python in this course. If you have little or no experience coding in Python, you should either follow a Python tutorial before the course starts, or prepare to invest some hours getting up to speed with the language once we start.
Faculty Members:

TBA
Program Contact:

Natalia Landázuri, Ph.D., csc-engr@disstockholm.se 
Time & Place:

TBA

 

Course Description

Spotify, the Swedish giant, relies on machine learning to personalize the music experience of millions of users. Scania, the Swedish world-leader provider of transport solutions, utilizes machine learning to develop self-driving trucks. Machine Learning is more ubiquitous in modern companies, and Sweden is a renowned hub for technical startups developing the future of machine learning. Applications include robotics, computer vision, speech recognition and synthesis, traffic predictions, and medical diagnostics.

Machine learning utilizes training data to develop models capable of identifying patterns, classifying large amounts of information, making predictions or decisions, and providing insights embedded in vast and complex data. This course offers a hands-on approach to the theory and practice of machine learning, with real-world applications. It focuses on understanding various types of data, training datasets, different machine learning approaches, and the optimization of models.

 

Learning outcomes

Knowledge/concepts that will be covered, discussed and acquired during the course:

  • Fundamentals of statistical learning
  • Supervised and unsupervised learning, with reflection and understanding of when these can be applied to real-world problems
  • Selected machine learning models and their mathematical foundation
  • Core principles and relevant pitfalls of training machine learning models
  • Neural networks and deep learning (introductory material)
  • Machine learning as a core technology in modern society

Skills that will be acquired during the course:

  • Application of fundamental supervised machine-learning models in python (e.g. linear and non-linear regression and classification)
  • Application of fundamental unsupervised machine learning models for clustering
  • Analysis of model generalizability
  • Dimensionality reduction and data visualization
  • Building of deep neural network models

 

Visits and field studies

Possible visits can include:

 

Approach to Learning

The course is designed around the principle of constructive alignment. The major components in the course—the assignments and the final project —implement this principle by stating clear goals and activities for every session and in the context of the course as a whole.

You are expected to engage actively in classroom discussions, presentations, exercises, and group work. In addition, you will participate in local field studies and extended course-integrated study tours in Sweden and Germany. These visits give you the opportunity to learn first-hand from leaders in the field of machine learning, to speak with professionals about their cutting-edge work, and to better understand specific approaches to research, development, implementation and utilization of machine learning.

 

Core Course Week and Study Tours

Core course week and study tours are integral parts of the core course. The classroom is “on the road” and theory presented in the classroom is applied in the field. You will travel with classmates and DIS faculty/staff on two study tours: a short study tour during the core course week and a long study tour to relevant European destinations. You are expected to

  • participate in all activities
  • engage in discussions, ask questions, and contribute to achieving the learning objectives
  • be respectful to the destination/location, the speakers, DIS staff, and fellow classmates
  • represent self, home university and DIS in a positive light

While on a program study tour, DIS will provide hostel/hotel accommodation, transportation to/from the destination(s), approx. 2 meals per day and entrances, guides, and visits relevant to your area of study or the destination. You will receive a more detailed itinerary prior to departure.

Travel policies: You are required to travel with your group to the destination. If you have to deviate from the group travel plans, you need approval from the program director and the study tours office. 

  

Expectations of the Students

You are expected to reach the preparation goal leading up to each session. If you have little or no experience coding in Python, you should either follow a Python tutorial before the course starts, or prepare to invest some hours getting up to speed with the language once we start. You should have a working laptop computer. It is advised that each machine has a least 4 GB of RAM and a reasonable processor (if it’s bought after 2014 you should be fine). The Unix operating system is preferred (OSX and Linux), but not a necessity.

 

Assignments, Evaluation and Grading

To be eligible for a passing grade in this class, all of the assigned work must be completed.

You are expected to turn in all the assignments on the due date. If an assignment is turned in after the due date, the grade of the assignment will be reduced by 10 points (over 100) for each day the submission is late.

During the course you will hand in two assignments containing selected exercises solved in class. Both project and assignments are group efforts. Furthermore, you will complete a larger project that uses tools which have been taught in the class. An acceptable project will cover e.g. feature extraction, analysis and modelling. You will be allowed to define your own project, but you can also get assistance from the teacher.

During the programming projects, you are allowed to consult freely with any of the other students and the instructor. Contributions from other students, however, must be acknowledged with citations in your final report, as required by academic standards. Contributions to your presentations must similarly be acknowledged. Needless to say, the right to consult does not include the right to copy — programs, papers, and presentations must be your own original work. 

Assignments: Leading up to each session, you are given a "preparation goal" and a suggested list of materials you can use to reach it. Sessions start with a short lecture (around 1 hour) that introduces the topic of the day. You work through a set of technical exercises. You are required to hand in two assignments throughout the course (40% of the final grade, 20% each), which are composed of selected problems from the exercises you have solved in class. This gives you a clear outcome goal for each session: "show up prepared and complete the exercises". It gives you incentive to be prepared and focus on the work.

Final project: From the beginning of the course, you are aware that an important outcome of the course is a project that could add value to your professional portfolio. To accomplish the project, you will work in teams. Each team selects a popular topic of their interest, and investigates it using data that needs to scraped or downloaded from the Internet. Student teams submit the project in two parts. First, each team must prepare a proposal presentation/video which demonstrates that they have a sound plan for their project and have clear hypotheses related to expected outcomes. The proposal presentation/video is a fun exercise that serves as a platform for sharing ideas between groups (we view them all in class). In addition, it helps you start with a comprehensive idea of an outcome in mind. Second, once the project is finalized, student teams are required to communicate the results in the popular format of a blog post. 

Participation grade: it reflects your contribution to classes, exercises, comments on other students' questions on the Discussion boards, attendance and engagement with guest speakers and during field studies.  Inappropriate and/or unprofessional behaviour (e.g., sleeping during presentations, being rude towards our hosts during field studies) results in a score of 0 for participation for the entire semester.

 

When assigning the final grades, your efforts will weigh as follows: 

  • Participation: 20% (includes participation in class,exercises and project, as well as behavior that is beneficial to the learning of peers)
  • Mandatory assignments: 40% (two hand-ins, each counting for 20%)
  • Final project: 40% (10% proposal presentation, 30% project report and presentation) 

 

Readings

Machine Learning: An Algorithmic Perspective, Second Edition; Stephen Marsland - Chapters 2, 3, 4, 6, 9, 12 and 14

The Python Data Science Handbook; Jake Vanderplaas - Chapters 2, 3, 4 and 5

Domingos, Pedro. "A few useful things to know about machine learning." Communications of the ACM 55.10 (2012): 78-87.

 

Faculty

TBA

 

Course Summary

The course is rooted in 9 major topics followed by project work, which will be covered during 18 sessions (80-min each), field studies, core course week, and long study tour.

  1. Thinking about data, feature extraction, PCA (principal component analysis)
  2. Measures of similarity, summary statistics, probabilities
  3. Probability densities, data visualization
  4. Linear regression, decision trees
  5. Decision trees revisited, nearest neighbors, model evaluation
  6. AUC (area under the curve), neural networks & deep learning
  7. Hierarchical clustering, K-means
  8. Density estimation, mixture models
  9. Bias/Variance, Project proposals
  10. Lab work on project report
  11. Lab work on project report
  12. Project presentations

 

 

Academic Regulations  

Please make sure to read the Academic RegulationsLinks to an external site. on the DIS website. There you will find regulations on:

 

DIS - Study Abroad in Scandinavia - www.DISabroad.orgLinks to an external site.

 

 

Course Summary:

Date Details Due