VladMB/soft2019spring-ai

AI/ML course content

Introduction

The Machine Learning & AI course is one of two elective courses on the 1./2. semester of the Bachelor programme at Cphbusiness/Lyngby SOFT. It is taught this semester (2019, spring) by Jens Egholm Pedersen (JEEP) and Jacob Trier Frederiksen (JTF).

• General information on the courses of spring 2019 semester is on GitHub here:

  • https://datsoftlyngby.github.io/soft2019spring/

• Specific information on ML & AI course is on GitHub here:

  • https://datsoftlyngby.github.io/soft2019spring/AI_plan.html

• Course books:

  • 100 page ML book: http://themlbook.com/wiki/doku.php
  • Hands-on ML with Scikit-Learn, Keras and Tensorflow: https://github.com/ageron/handson-ml2

• Course work material is on GitHub, here:

  • https://github.com/datsoftlyngby/soft2019spring-ai

We shall use the following resource infrastructure:

Moodle

• We will use the courses' Moodle Flow for announcements to the class.

GitHub

• Will be used extensively for relaying course materials, so link it in.

Peergrade

• All hand-in assignments are subject to peer review (you "grade" your fellow students), and will be conducted through Peergrade. You will receive information from us on how to sign up and participate in due time.

Mentimeter

• For active participation during class hours, we shall use the peer participation tool Mentimeter:. You will receive instructions from us in due time, during the course when active participation is warranted (or required).

Additional resources

There exists a ton of resources that helps you understand the material. Be proactive: find the video/books/games/friends that helps you learn! We added some resources to things that might help you:

Source	Material	Link
Khan Academy	Intuitive and friendly math videos	https://www.khanacademy.org/
3blue1brown	Great visualisations of math topics, for instance dot products, linear algebra and gradient descent.	https://www.3blue1brown.com/
Towards machine learning	Real-world topics on ML, with great examples of for instance linear regression and clustering.	https://towardsdatascience.com/
Kaggle	Cool place for machine learning projects and competition (with real prizes!)	https://www.kaggle.com/
List of awesome ML resources	A near-endless list of ML frameworks, libraries and software	https://github.com/josephmisiti/awesome-machine-learning
List of awesome AI resources	A long list of AI courses, tools, apps, etc.	https://github.com/hades217/awesome-ai
List of aweful AI resources	A list of bad and scary AI things	https://github.com/daviddao/awful-ai