|
|
Main menu for Browse IS/STAG
Course info
KIV / SU
:
Course description
Department/Unit / Abbreviation
|
KIV
/
SU
|
Academic Year
|
2023/2024
|
Academic Year
|
2023/2024
|
Title
|
Machine Learning
|
Form of course completion
|
Exam
|
Form of course completion
|
Exam
|
Accredited / Credits
|
Yes,
6
Cred.
|
Type of completion
|
Combined
|
Type of completion
|
Combined
|
Time requirements
|
Lecture
3
[Hours/Week]
Tutorial
2
[Hours/Week]
|
Course credit prior to examination
|
Yes
|
Course credit prior to examination
|
Yes
|
Automatic acceptance of credit before examination
|
No
|
Included in study average
|
YES
|
Language of instruction
|
Czech
|
Occ/max
|
|
|
|
Automatic acceptance of credit before examination
|
No
|
Summer semester
|
0 / -
|
0 / -
|
0 / -
|
Included in study average
|
YES
|
Winter semester
|
11 / -
|
7 / 50
|
0 / 5
|
Repeated registration
|
NO
|
Repeated registration
|
NO
|
Timetable
|
Yes
|
Semester taught
|
Winter semester
|
Semester taught
|
Winter semester
|
Minimum (B + C) students
|
10
|
Optional course |
Yes
|
Optional course
|
Yes
|
Language of instruction
|
Czech
|
Internship duration
|
0
|
No. of hours of on-premise lessons |
|
Evaluation scale |
1|2|3|4 |
Periodicity |
každý rok
|
Evaluation scale for credit before examination |
S|N |
Periodicita upřesnění |
|
Fundamental theoretical course |
No
|
Fundamental course |
Yes
|
Fundamental theoretical course |
No
|
Evaluation scale |
1|2|3|4 |
Evaluation scale for credit before examination |
S|N |
Substituted course
|
KIV/TKS
|
Preclusive courses
|
KIV/SU-E and KKY/USK
|
Prerequisite courses
|
N/A
|
Informally recommended courses
|
KMA/LAA and KMA/MA1 and KMA/PSA and KIV/TI
|
Courses depending on this Course
|
KIV/ADSZ, KIV/NLP, KIV/PMZD, KIV/SZD
|
Histogram of students' grades over the years:
Graphic PNG
,
XLS
|
Course objectives:
|
To provide the students with the necessary theoretical knowledge and practical skills to understand the fundamental principles of machine learning techniques as of the key area of artificial intelligence; to understand in depth both theoretically and practically the basic methods from which the current modern machine learning techniques and techniques of knowledge representation and transformation are derived. Emphasis is placed on the interconnection of the related knowledge from mathematics, theoretical computer science, probability and statistics, and other theoretical prerequisites with a practical engineering approach to machine learning techniques and practices for the implementation and deployment of artificial intelligence in industry.
|
Requirements on student
|
A student obtains accreditation iff he or she hands in his/her seminar work according to preselected assignment in due time. The seminar work is a solo work of larger extent implemented in a common programming language (MATLAB/Octave/Python). The topic of the work can be devised (brought forward) be the student him-/herself (and had approved by the teacher) or chosen from topics that (co-)form the scientific research programme of the department.
The exam is oral with the goal to verify the depth of understanding the problems that the subject deals with. A student draws lots to get one topic out of the list of the exam topics. Then he/she has 30 minutes for preparation and subsequently discusses the drawn topic in details.
|
Content
|
The below itemized topics represent radii of the subject matter went through, they do not exactly correspond to scheduled lectures:
1. Introductory information, organization of the subject, recommended literature andsources of study materials; basic notion and definitions of the cognitive systems theory, relationship among data, information and knowledge, components of cognitive systems, general classification task.
2. Introduction into machine learning, supervised and unsupervised learning, applications and examples, case studies.
3. Bayes learning, Bayes theorem, optimal and naive bayesian classifier, hypothesis selection strategies, applications of NBC.
4. Linear regression, cost function derivation and techniques to minimize it, gradient descent derivation, gradient descent algorithm.
5. Multivariate linear regression, gradient descent in multidimensional space, problems and limitations of gradient descent; polynomial regression; normal equation.
6. Logistic regression, logistic regression hypothesis model, interpretation of the results, decision boundary, multi-class classification - One-vs-All algorithm.
7.Regularization, overtraining and its symptoms, techniques to avoid/suppress overtraining, naive derivation of regularization, regularization algorithm, regularized linear and logistic regression.
8. Support Vector Machines, optimization goal as an alternative perspective of logistic regression, mathematical model of SVM, hypothesis with safety factor, kernels.
9. Neural networks, history, biological pre-model of artificial neural networks, mathematical model of a neuron, MLP-type layered networks, classification via ANN, cost function of an ANN and its optimization, learning, Backpropagation algorithm.
10. Clustering, general remarks on unsupervised learning, K-means method, optimization criterion of the K-means, centroid selection, cluster number selection, K-means algorithm.
11. Dimensionality reduction, Principal Component Analysis, PCA functionality description and algorithm, PCA features, mathematical background of PCA, applications and case studies.
12. Blind source separation, motivation and definition of the blind source separation problem, Independent Component Analysis, ICA functionality description and algorithm, ICA features, mathematical background of ICA, applications and case studies.
|
Activities
|
|
Fields of study
|
|
Guarantors and lecturers
|
|
Literature
|
-
Basic:
Bishop, C.M. Pattern Recognition and Machine Learning. Springer, 2006. ISBN 978-0387-31073-2.
-
Basic:
Trevor Hastie, Robert Tibshirani, Jerome Friedman. The Elements of Statistical Learning. Springer. 2009. ISBN 978-0-387-84857-0.
-
Recommended:
Barber, David. Bayesian reasoning and machine learning. Cambridge : Cambridge University Press, 2012. ISBN 978-0-521-51814-7.
-
Recommended:
Heylighen, Francis. Cognitive Systems - A Cybernetic Perspective on the New Science of the Mind. Lecture Notes.. ECCO: Evolution, Complexity and Cognition. Vrije Universiteit Brusse, 2010.
-
Recommended:
Nilsson, J. Nils. Introduction to Machine Learning. Stanford University Press. Stanford University, 2005.
-
On-line library catalogues
|
Time requirements
|
All forms of study
|
Activities
|
Time requirements for activity [h]
|
Graduate study programme term essay (40-50)
|
40
|
Preparation for an examination (30-60)
|
30
|
Preparation for laboratory testing; outcome analysis (1-8)
|
15
|
Practical training (number of hours)
|
26
|
Contact hours
|
39
|
Presentation preparation (report) (1-10)
|
6
|
Total
|
156
|
|
Prerequisites
|
Knowledge - students are expected to possess the following knowledge before the course commences to finish it successfully: |
kreativně aplikovat matematické poznatky s cílem nazírat na úlohy strojového učení jako na problém prohledávání N-dimenzionálního stavového prostoru |
prakticky využívat nabyté znalosti z matematické analýzy, lineární algebry, pravděpodobnosti a statistiky |
prakticky využívat nabyté znalosti z oblasti umělé inteligence a rozpoznávání |
popsat pojmy a struktury teoretické informatiky, orientují se v základech výrokové i predikátové logiky |
Skills - students are expected to possess the following skills before the course commences to finish it successfully: |
programovat na pokročilé úrovni v některém z vyšších programovacích jazyků, např. C++, C#, Object Pascal, SCALA, Java; praktická znalost MATLABu či Octave výhodou |
studovat odborné texty v anglickém jazyce |
Competences - students are expected to possess the following competences before the course commences to finish it successfully: |
N/A |
|
Learning outcomes
|
Knowledge - knowledge resulting from the course: |
dosáhnout hlubšího pochopení základních technik strojového učení, reprezentace, odvozování a ukládání znalostí a racionálního chování, tj. rozhodování a řešení problémů |
orientovat se v paradigmatech učících se systémů, zejména s přihlédnutím k jejich praktické aplikaci v oblasti umělé inteligence a inteligentního software |
Skills - skills resulting from the course: |
analyzovat existujiící algoritmy strojového učení a jejich teoretické specifikace v odborné literatuře |
implementovat učící se algoritmy |
orientovat se v existujících implementacích učících se algoritmů, zejména s ohledem na jejich modifikaci, příp. optimalizaci |
zapojit se do řešení vědecko-výzkumných úkolů v oblasti umělé inteligence a strojového učení v rámci dalšího studia |
Competences - competences resulting from the course: |
N/A |
|
Assessment methods
|
Knowledge - knowledge achieved by taking this course are verified by the following means: |
Combined exam |
Test |
Skills - skills achieved by taking this course are verified by the following means: |
Seminar work |
Competences - competence achieved by taking this course are verified by the following means: |
Combined exam |
|
Teaching methods
|
Knowledge - the following training methods are used to achieve the required knowledge: |
Discussion |
Individual study |
Interactive lecture |
Lecture supplemented with a discussion |
Lecture with visual aids |
Self-study of literature |
Task-based study method |
Skills - the following training methods are used to achieve the required skills: |
Lecture with visual aids |
Competences - the following training methods are used to achieve the required competences: |
Task-based study method |
|
|
|
|