ARTIFICIAL LEARNING
| Title | ΤΕΧΝΙΚΕΣ ΜΗΧΑΝΙΚΗΣ ΜΑΘΗΣΗΣ / ARTIFICIAL LEARNING |
| Code | ΔΜ1025 |
| Interdepartmental Programme | PPS Advanced Computer and Communication Systems |
| Collaborating Schools | Electrical and Computer Engineering Medicine Music Studies Journalism and Mass Communications |
| Cycle / Level | 1st / Undergraduate, 2nd / Postgraduate |
| Teaching Period | Winter/Spring |
| Coordinator | Christos Diou |
| Common | Yes |
| Status | Active |
| Course ID | 600004438 |
Programme of Study: PPS Advanced Computer and Communication Systems
Registered students: 0
| Orientation | Attendance Type | Semester | Year | ECTS |
|---|---|---|---|---|
| EUFYĪ KAI AUTONOMA SYSTĪMATA-METHODOLOGIES YPOLOGISTIKĪS NOĪMOSYNĪS KAI EFARMOGES | Compulsory Course | 1 | 1 | 5 |
Programme of Study: PPS Advanced Computer and Communication Systems
Registered students: 16
| Orientation | Attendance Type | Semester | Year | ECTS |
|---|---|---|---|---|
| Eyfyī systīmata-Methodologíes ypologistikīs noīmosýnīs kai efarmogés | Compulsory Course | 2 | 1 | 5 |
| Diktyakī Ypologistikī- Īlektronikó Ebório | Elective Courses | 2 | 1 | 5 |
| Academic Year | 2017 – 2018 |
| Class Period | Spring |
| Faculty Instructors | |
| Instructors from Other Categories | |
| Weekly Hours | 24 |
| Class ID | 600116452
|
Course Type 2016-2020
- Scientific Area
Course Type 2011-2015
Specific Foundation / Core
Mode of Delivery
- Face to face
Digital Course Content
- e-Study Guide https://qa.auth.gr/en/class/1/600116452
Language of Instruction
- Greek (Instruction, Examination)
- English (Examination)
Prerequisites
General Prerequisites
Calculus of single and many variable functions, linear algebra. Matlab Programming.
Learning Outcomes
This course aims at a balanced presentation of theoretical concepts and practical applications. The goal is to learn the motivation behind several machine learning algorithms , with an introductory mathematical treatment and then concetrate on their applications. Upon succesful completion of the course, the student should be able to apply a large number of ML algorithms to practical problems.
Course Content (Syllabus)
Supervised learning: LMS, Logistic regression, Perceptron, Gaussian discriminant analysis, Naive Bayes, Support vector machines, Model selection and feature selection.
Unsupervised learning: Clustering. K-means. EM Algorithm . Mixture of Gaussians.
Reinforcement learning and control: MDPs. Bellman equations.
Value iteration and policy iteration. Q-learning. Value function approximation. Policy search. Reinforce. POMDPs.
Learning theory: Bias/variance tradeoff, VC dimension, Online learning
Course Organization
| Activities | Workload | ECTS | Individual | Teamwork | Erasmus |
|---|---|---|---|---|---|
| Lectures | 26 | ||||
| Total | 26 |
Student Assessment
Description
Term project, written final exam.
Bibliography
Additional bibliography for study
Hastie, Friedman, and Tibshirani, The Elements of Statistical Learning, 2001
Bishop, Pattern Recognition and Machine Learning, 2006
Ripley, Pattern Recognition and Neural Networks, 1996
Mitchell, Machine Learning, 2000
Duda, Hart, and Stork, Pattern Classification, 2nd Ed., 2002
Tan, Steinbach, and Kumar, Introduction to Data Mining, Addison-Wesley, 2005.
Mardia, Kent, and Bibby, Multivariate Analysis, 1979
Sutton and Barto, Reinforcement Learning: An Introduction, MIT Press, 1998.
Bertsekas and Tsitsiklis, Neuro-Dynamic Programming, Athena Scientific, 1996.
Last Update
23-09-2013
