Pattern Recognition and Machine Learning
| Title | Αναγνώριση Προτύπων και Μηχανική Μάθηση / Pattern Recognition and Machine Learning |
| Code | 109 |
| Faculty | Engineering |
| School | Electrical and Computer Engineering |
| Cycle / Level | 1st / Undergraduate |
| Teaching Period | Winter |
| Coordinator | Panagiotis Petrantonakis |
| Common | Yes |
| Status | Active |
| Course ID | 600001074 |
Programme of Study: Electrical and Computer Engineering
Registered students: 136
| Orientation | Attendance Type | Semester | Year | ECTS |
|---|---|---|---|---|
| ELECTRICAL ENERGY | Elective Courses | 7 | 4 | 5 |
| ELECTRONICS AND COMPUTER ENGINEERING | Elective Courses | 7 | 4 | 5 |
| TELECOMMUNICATIONS | Elective Courses | 7 | 4 | 5 |
| Academic Year | 2021 – 2022 |
| Class Period | Winter |
| Faculty Instructors | |
| Class ID | 600196644
|
Course Type 2016-2020
- Scientific Area
Course Type 2011-2015
Specific Foundation / Core
Mode of Delivery
- Face to face
- Distance learning
Digital Course Content
Language of Instruction
- Greek (Instruction, Examination)
- English (Examination)
Prerequisites
General Prerequisites
1. Probabilistic Theory and Statistics
2. Basic knowledge of Logic Programming
3. Basic knowledge of Data Structures
Learning Outcomes
By the end of the course students are expected to:
a) Know the basic principles of pattern recognition theory and the main application domains
b) Understand the fundamental pattern recognition methods and algorithms
c) Apply well-known algorithms to pilot problems
d) Select the most efficient algorithm, based on problem requirements
e) Design the methodology for pattern recognition problems of medium complexity
General Competences
- Apply knowledge in practice
- Retrieve, analyse and synthesise data and information, with the use of necessary technologies
- Make decisions
- Work in teams
- Be critical and self-critical
- Advance free, creative and causative thinking
Course Content (Syllabus)
Pattern recognition focuses on the design of systems capable of extracting patterns from data. Issues related to feature extraction, error estimation and model statistics are also discussed. State-of-the art fields such as Machine learning, Data mining, Computer vision and Human Computer Interaction employ Pattern Recognition principles.
Topics covered within the context of the course:
a) Introduction to Pattern Recognition principles
b) Data preprocessing and exploration
c) Classification: Basic principles, Model evaluation, Bayesian algorithms, Decision trees, SVMs (linear/non-linear), Perceptrons, Classifier Ensembles
d) Clustering: Basic principles, Model evaluation, Partitioning algorithms, Hierarchical algorithms, Density-based algorithms, SOMs, Mixture models
e) Data reduction (PCA, ISOMAP)
Keywords
Data Analysis, Classification, Clustering, Pattern recognition
Educational Material Types
- Notes
- Slide presentations
- Interactive excersises
- Book
- 1 project
Use of Information and Communication Technologies
Use of ICT
- Use of ICT in Course Teaching
- Use of ICT in Laboratory Teaching
- Use of ICT in Communication with Students
Description
E-learning, a moodle-based system has been customized by the university IT team. It allows instructors to post announcements, communicate with students, upload lectures, exercises and their solutions, set up and run course projects, while it also offers self-assessment capabilities. E-learning also supports a Forum for coursework discussion.
Course Organization
| Activities | Workload | ECTS | Individual | Teamwork | Erasmus |
|---|---|---|---|---|---|
| Lectures | 39 | 1.3 | ✓ | ||
| Laboratory Work | 16 | 0.5 | ✓ | ||
| Tutorial | 27 | 0.9 | |||
| Written assigments | 44 | 1.5 | ✓ | ✓ | |
| Exams | 24 | 0.8 | |||
| Total | 150 | 5 |
Student Assessment
Description
This module utilises a grading system extending from 1 to 10 (where 1 is the lowest and 10 is the highest available mark). An overall mark of 5 or higher is required for successful completion of the module otherwise students will be asked to repeat the course the next academic year. The overall mark is rounded to the nearest half number.
The mark for this module is a weighted average based on:
1. An assessment on two online quizzes (Classification - 45%, Clustering - 55%)
2. A final online exam (both Classification and Clustering - 100%)
Participation in 1. is obligatory, while participation in 2. is optional.
The final mark is the maximum between 1. and 2.
Student Assessment methods
- Written Assignment (Summative)
- Oral Exams (Formative)
- Written Exam with Problem Solving (Formative)
- Report (Formative)
Bibliography
Course Bibliography (Eudoxus)
1. Τίτλος Συγγράμματος: «Αναγνώριση Προτύπων», Συγγραφέας: Σ. Θεοδωρίδης, Κ. Κουτρουμπάς, Εκδόσεις: 2011 Πασχαλίδης ή BROKEN HILL PUBLISHERS LTD
ISBN: 9789604891450, Κωδικός Βιβλίου στον Εύδοξο: 13256974
2. Τίτλος Συγγράμματος: «Εισαγωγή στην εξόρυξη δεδομένων», Συγγραφέας: Tan Pang - Ning,Steinbach Michael,Kumar Vipin, Εκδόσεις: Α. ΤΖΙΟΛΑ & ΥΙΟΙ Α.Ε. 2010, ISBN: 978-960-418-162-9, Κωδικός Βιβλίου στον Εύδοξο: 18549105
3. Τίτλος Συγγράμματος: «Αναγνώριση Προτύπων», Συγγραφέας: Μ. Στρίντζης, Εκδόσεις: Κυριακίδη 2007, ISBN: 978-960-343-290-6, Κωδικός Βιβλίου στον Εύδοξο: 6378
Additional bibliography for study
Τίτλος Συγγράμματος: «Εισαγωγή στην αναγνώριση προτύπων με Matlab»
Συγγραφέας: THEODORIDIS S., PIKRAKIS A., KOUTROUMBAS K., CAVOURAS D.
Εκδόσεις: 2011 Πασχαλίδης ή BROKEN HILL PUBLISHERS LTD
ISBN: 9789604890231
Κωδικός Βιβλίου στον Εύδοξο: 13256624
Τίτλος Συγγράμματος: «Αναγνώριση Προτύπων»,
Συγγραφέας: Μ. Στρίντζης
Εκδόσεις: Κυριακίδη 2007
ISBN: 978-960-343-290-6
Κωδικός Βιβλίου στον Εύδοξο: 6378
Last Update
01-09-2021
