ARTIFICIAL LEARNING

Course Information
TitleΤΕΧΝΙΚΕΣ ΜΗΧΑΝΙΚΗΣ ΜΑΘΗΣΗΣ / ARTIFICIAL LEARNING
CodeΔΜ1025
Interdepartmental ProgrammePPS Advanced Computer and Communication Systems
Collaborating SchoolsElectrical and Computer Engineering
Medicine
Music Studies
Journalism and Mass Communications
Cycle / Level1st / Undergraduate, 2nd / Postgraduate
Teaching PeriodWinter/Spring
CoordinatorChristos Diou
CommonYes
StatusActive
Course ID600004438

Programme of Study: PPS Advanced Computer and Communication Systems

Registered students: 0
OrientationAttendance TypeSemesterYearECTS
EUFYĪ KAI AUTONOMA SYSTĪMATA-METHODOLOGIES YPOLOGISTIKĪS NOĪMOSYNĪS KAI EFARMOGESCompulsory Course115

Programme of Study: PPS Advanced Computer and Communication Systems

Registered students: 0
OrientationAttendance TypeSemesterYearECTS
Eyfyī systīmata-Methodologíes ypologistikīs noīmosýnīs kai efarmogésCompulsory Course215
Diktyakī Ypologistikī- Īlektronikó EbórioElective Courses215

Class Information
Academic Year2018 – 2019
Class PeriodSpring
Faculty Instructors
Instructors from Other Categories
Weekly Hours24
Class ID
600138579
Course Type 2016-2020
  • Scientific Area
Course Type 2011-2015
Specific Foundation / Core
Mode of Delivery
  • Face to face
Digital Course Content
Language of Instruction
  • Greek (Instruction, Examination)
  • English (Examination)
Prerequisites
General Prerequisites
Calculus of single and many variable functions, linear algebra. Basic programming skills.
Learning Outcomes
This course aims at introducing machine learning algorithms and techniques, including theory and practicall applications. The course includes: - Single and multiple linear regression, as well as their nonlinear variants - Logistic regression and Linear Discriminant Analysis for classification - Capacity control and regularization - Nonparametric classifiers and introduction to Support Vector Machines - Nonlinear SVMs and Kernels - Other SVM variants - Ensemble learning methods - Random forests, EXTRA trees, gradient boosting trees - Practical applications, hyperparameter selection and evaluation metrics The course includes practical examples in Python, using scikit-learn. Evalution will take place using projects that will be handed out during the course.
General Competences
  • Apply knowledge in practice
  • Retrieve, analyse and synthesise data and information, with the use of necessary technologies
  • Adapt to new situations
  • Make decisions
  • Work autonomously
  • Generate new research ideas
  • Advance free, creative and causative thinking
Course Content (Syllabus)
The course includes: - Single and multiple linear regression, as well as their nonlinear variants - Logistic regression and Linear Discriminant Analysis for classification - Capacity control and regularization - Nonparametric classifiers and introduction to Support Vector Machines - Nonlinear SVMs and Kernels - Other SVM variants - Ensemble learning methods - Random forests, EXTRA trees, gradient boosting trees - Practical applications, hyperparameter selection and evaluation metrics The course includes practical examples in Python, using scikit-learn. Evalution will take place using projects that will be handed out during the course.
Educational Material Types
  • Slide presentations
  • Book
Course Organization
ActivitiesWorkloadECTSIndividualTeamworkErasmus
Lectures26
Total26
Student Assessment
Description
Individual projects
Bibliography
Additional bibliography for study
1. Christopher Bishop, "Pattern recognition and machine learning". Springer, 2006 2. Alex Smola and S.V.N. Vishwanathan, "Introduction to machine learning", Cambridge university press, 2008 Διαθέσιμο online: http://alex.smola.org/drafts/thebook.pdf 3. Trevor Hastie, Robert Tibshirani, Jerome Friedman, "The elements of statistical learning: Data mining, inference and prediction", 2nd edition, Springer, 2008 Διαθέσιμο online: https://web.stanford.edu/~hastie/Papers/ESLII.pdf 4. Ian Goodfellow, Yoshua Bengio and Aaron Courville, "Deep learning", MIT press, 2016 Διαθέσιμο online: https://www.deeplearningbook.org/ 5. Aurelien Geron, "Hands-on machine learning with scikit-learn and Tensorflow: Concepts, tools and techniques to build intelligent systems", O'Reilly, 2017
Last Update
05-02-2019