INAIO1100 Introduction to Artificial Intelligence and Machine Learning Course description

This course provides an introduction to artificial intelligence (AI) and machine learning (ML). The students are going to obtain an overview of the main methods in AI and ML, as weel as the practical understanding of the methods being taught. The students will have the opportunity to use and implement these methods, and also to implement a combination of these methods into their own projects. The course covers expert systems, supervised classification and regression (including artificial neural networks and deep learning), unsupervised learning (clustering, dimensionality reduction and association rules), genetic and evolutionary algorithms and search methods, optimization and reinforcement learning. In addition, the students will learn about the how to evaluate their methods and how to overcome common challenges. The students will also be introduced to a socio-historical critical view of AI and ML where the students will get in contact with diverse perspectives on the ethical, legal and social considerations around AI and ML. Students without previous programming background will receive a brief introduction to using the command line, version control and python.

Knowlege of programming, Statistics and Calculus is an advatage for the practical section of the course. The theoretical part of the course requires no specific background.

Knowledge

On successful completion of this course the student has knowledge of:

• the history of AI, its current trends and breakthroughs as well as its current challenges.
• the main areas and methods of AI including machine learning, computer vision, natural language processing and deep learning.
• the theoretical and practical aspects involved in designing and employing AI technologies.
• the multiple use-cases for AI in different professional sectors. Its value propositions and their business models.
• the issues that AI brings to ethics, economy and work-labor market.
• the most common problems in applying AI/ML methods and the most common solutions to overcome them.

Skills

On successful completion of this course the student has the ability to:

• identify and discriminate the problems that may be solved with AI technologies.
• know which AI methodology is most suitable to solve a problem.
• implement in code a broad set of AI/ML methods using python and standard packages.
• understand how their professional lives may be affected (improved or threatened) by AI technologies

General competences

On successful completion of this course the student can apply:

• the theory underlying AI and its history to better understand the consequences of AI in society.
• their knowledge to solve simple data/rule driven problems.

Lectures, group discussions, and guided tutorials using pre-developed AI models in Python using Jupyter Notebooks.

Practical lessons will be given as Stand-Alone Workshops that can be taken asynchronously or out of order.

Theoretical lessons will be given through videos, quizzes and self guided exercises in canvas.

The course has 12 modules. There is a mandatory assignment for each module.

Video oral presentation. The oral exam cannot be appealed.

All materials, sources and resources are allowed during the exam.

Graded in the scale from A to F.

Two examiners will be used. External examiner is used regularly.

Gustavo Borges Moreno e Mello

This course has 2,5 ECTS overlapping content with INAIO1000.