|Lecturers||Tomi Janhunen and Alex(ander) Jung|
Ivan Afonichkin, Buse Atli, Eric Bach, Ivan Baranov, Jori Bomanson, Pihla Karanko, Stefan Mojsilovic, Teemu Pudas, Matilde Tristany Farinha, Antonius Weinzierl
|Workload||Lectures 20h, exercise sessions 20h, independent work 90h, examination 3h|
Artificial intelligence (AI) tackles complex real-world problems, such as question answering, speech recognition, social network analysis, and task scheduling, with rigorous mathematical methods and tools. The goal of this course is to give an in-depth introduction to AI methodology while approaching the topic from the perspective of concrete application problems. Having completed the course, you have gained a comprehensive overview of AI and understand its fundamental principles related to machine learning and logical reasoning. You have excellent premises for solving real-world problems with modern AI techniques and building intelligent systems by implementing such techniques.
The course presents a range of central AI techniques and provides the students with an extensive toolbox for solving problems in practice. For applications that require high degree of adaptation, specific techniques such as (deep) machine learning, reinforcement learning, and graphical models are included. These methods are instrumental for decision under uncertainty. For the purposes of knowledge representation and reasoning, different logical representations such as formulas, circuits, and rules are covered. These representations establish the foundations for declarative problem solving and enable the use of state-of-the-art solver technology to search for solutions. The course also encourages the students to combine the logical and machine learning perspectives when solving future problems.
11.01.2018: Introduction (What? Why? How?)
18.01.: Search (Basic Problem Solving)
25.01.: Markov Decision Processes (The World Seen by A Cleaning Robot)
01.02.: Logical Reasoning (How to Implement Exact Reasoning with a Computer?)
08.02.: Logic Programming (Problem Solving via Declarative Programming)
22.02.: Elements of Machine Learning (How Does a Robot Perceive its Environment?)
01.03.: Reinforcement Learning (How To Find Optimal Decisions On-The-Fly?)
08.03.: Logical Applications (Increasing Appetite by Seeing What Can be Done)
15.03.: Graphical Models (How To Handle a Large Number of Random Variables?)
22.03.: Wrap Up (Synthesis)