Lectures

Lectures

Lectures Held on a Regular Basis

Please click here to find the lectures that are held on a regular basis. This information can be used to create a study plan. However, this information is tentative, i.e. always check the lectures of the current and next semester to keep the study plan up to date.

Lectures of the Current Semester

Module details on 'Machine Learning - Machine Learning'

CategoryData & Information
TypeLecture
SiteHannover
LecturerDr.rer.nat. Diaz-Aviles, Ernesto (Hannover)
Module Exam ID2038
ECTS-Credits5
Weekly Composition2L+1E
Required Hours of Work (presence / self-study)125 (42 / 83)
SemesterWinter
Teaching MethodsSlide presentations, exercises, discussions, homework and programming assignments
Module DescriptionMachine learning is the field of study of getting computers to learn and act without being explicitly programmed. Machine learning is widely used in science, industry, government and business. In the past decade, machine learning has provided feasible and cost-effective means for web search, computer vision, smart robots, speech recognition and other areas of AI. This course provides a broad introduction to machine learning, data mining, and statistical pattern recognition. Most of the class will be focused on supervised learning, which can be considered the most mature and widely used type of machine learning. We will also explore the most popular Unsupervised learning techniques: clustering and dimensionality reduction. Furthermore, during the course, we will discuss best practices in machine learning and provide practical advice for applying learning algorithms. In the class projects you will build your own implementations of machine learning algorithms and apply them to problems like text recognition, spam filtering and recommender systems. This will give you the insights and tools needed to become an expert in this exiting field.
Module OutcomesUpon completion of the course, students will be able to: 1. Understand the fundamentals of machine learning, data mining, and statistical pattern recognition 2. Implement, debug, and evaluate state-of-the-art machine learning algorithms 3. Correctly apply machine learning algorithms to problems like text recognition, spam filtering and recommender systems
Recommended LiteratureWe will provide lecture notes to cover the material. There is no single book that cover every aspect of the course. Some of the sources include: • Christopher M. Bishop. Pattern Recognition and Machine Learning. Springer-Verlag, 2006 • R.O. Duda, P.E. Hart, and D.G. Stork. Pattern Classification. John Wiley & Sons, 2001 • Thomas M. Mitchell. Machine Learning. McGraw-Hill, 1997
PrerequisitesThe main prerequisite for this class is basic knowledge of programming, that is, we assume that you know how to program in at least one programming language. Some previous exposure to probability, statistics, linear algebra, calculus and/or logic is useful but not essential. We will cover the basic concepts and go over the math concepts you need in the first couple of weeks.
ExamWritten exam, graded (90 min)
CommentsStart date: 2013-10-15 Location: Appelstrasse 4 (KBS) Second floor Room: 235 Hannover Schedule: Tuesdays: 14:45 - 16:15 (Lecture) Wednesdays: 14:45 - 15:30 (Exercises)

Available Course Modes

In the following document you can get an overview about the available course modes that are offered in the ITIS Master's program: Course Modes