Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
The scientific discipline of Machine Learning focuses on developing algorithms to find patterns or make predictions from empirical data. It is a classical sub-discipline within Artificial Intelligence (AI). The discipline is increasingly used by many professions and industries to optimize processes and implement adaptive systems. The course places machine learning in its context within AI and gives an introduction to the most important core techniques such as decision tree based inductive learning, inductive logic programming, reinforcement learning and deep learning through decision trees.INTENDED AUDIENCE: Interested studentsPREREQUISITES : Relevant applied math and statistics, core computer sciencelINDUSTRY SUPPORT : Broad industrial interest at present, i.e. for autonomous vehicles, robots, intelligent assistants and general datamining
Syllabus
Week 1: Introduction to the Machine Learning course
Week 2: Characterization of Learning Problems
Week 3: Forms of Representation
Week 4: Inductive Learning based on Symbolic Representations and Weak Theories
Week 5: Learning enabled by Prior Theories
Week 6: Machine Learning based Artificial Neural Networks
Week 7: Tools and Resources + Cognitive Science influences
Week 8: Examples, demos and exam preparations
Week 2: Characterization of Learning Problems
Week 3: Forms of Representation
Week 4: Inductive Learning based on Symbolic Representations and Weak Theories
Week 5: Learning enabled by Prior Theories
Week 6: Machine Learning based Artificial Neural Networks
Week 7: Tools and Resources + Cognitive Science influences
Week 8: Examples, demos and exam preparations
Taught by
Prof. Carl Gustaf Jansson Prof. Henrik Boström Prof. Fredrik Kilander