Subject

Knowledge Discovery with Deep Learning

Course Title

Knowledge Discovery with Deep Learning
Deep learning for knowledge discovery

Code

F23L3S106

Study Programme

—

Organizer of the study programme (unit, institute, department or division)

Faculty of Computer Science and Engineering

Degree level (first, second, third cycle)

First Cycle

Academic year / semester

8 / Summer

Number of ECTS credits

Teacher

Kire Trivodaliiev, Slobodan Kajaldzhijski, Sonja Gievska

Prerequisites for enrolling in the course

Artificial Intelligence or Introduction to Data Science or Machine Learning

10.

Objectives of the course programme (competences)

Upon completion of the course, the student will be able to select appropriate techniques for discovering and extracting knowledge from various types of data. The student will possess knowledge of advanced deep learning architectures with applications in recommendation systems, graph-structured data analysis, and multimodal data fusion.

11.

Course content

1. Introduction to the topics covered by the course. Advanced machine learning methods and areas of their application.
2. Graph-structured data. Analysis of the static and dynamic properties of graphs.
3. Application of Graph Neural Networks for Graph Analysis
4. Representation of nodes and edges in graphs
5. Knowledge extraction from social networks: Link prediction. Node classification and annotation.
6. Application of Graph Neural Networks for Recommendation Systems
7. Deep learning and supervised learning-based approaches
8. Generative Adversarial Networks
9. Application of GAN in machine vision and natural language processing
10. Multimodal fusion
11. Deep Neural Networks for Multimodal Fusion with Application Areas
12. Case studies of the application of reinforcement learning, graph neural networks, and generative adversarial networks

12.

Learning methods

Lectures supported by slide presentations, interactive lectures, practical classes (using equipment and software packages), teamwork, case studies, guest lecturers, independent preparation and defence of a project assignment and seminar paper, and learning in an electronic environment (forums and consultations).

13.

Total available time

6 ECTS x 30 hours = 180 hours

14.

Distribution of available time

30 + 45 + 15 + 15 + 75 = 180 hours

15.

Forms of teaching activities

15.1.	Lectures - theoretical instruction	30 hours
15.2.	Exercises (laboratory, auditory), seminars, teamwork	45 hours

16.

Other forms of activities

16.1.	Project assignments	15 hours
16.2.	Independent assignments	15 hours
16.3.	Home study	75 hours

17.

Assessment method

17.1.	Tests	0 points
17.2.	Seminar paper / project (presentation: written and oral)	15 points
17.3.	Activities and learning	10 points
17.4.	Final exam	10 points

18.

Grading criteria (points / grade)

up to 50 points	5 (five) (F)
from 51 to 60 points	6 (six) (E)
from 61 to 70 points	7 (seven) (D)
from 71 to 80 points	8 (eight) (C)
from 81 to 90 points	9 (nine) (B)
from 91 to 100 points	10 (ten) (A)

19.

Requirement for obtaining a signature and taking the final exam

501 points out of the 501 points available on the individual tasks were earned.

20.

Language of instruction

Macedonian and English

21.

Method for monitoring the quality of teaching

internal evaluation and survey mechanism

22.

Literature

22.1.	Required literature 1. David Easley & Jon Kleinberg \| Networks, Crowds, and Markets: Reasoning about a Highly Connected World \| Cambridge University Press \| 2010 2. J. Leskovec, A. Rajaraman, J. D. Ullman \| Mining of Massive Datasets \| Cambridge University Press \| 2014 3. Ian Goodfellow, Joshua Bengio, Aaron Courville \| Deep Learning \| MIT Press \| 2016
22.2.	Additional literature No. Author Title Publisher Year