Foundations of Deep Learning
BASIC DATA
course listing
A - main register
course code
ITI0233
course title in Estonian
Sügavõppe alused
course title in English
Foundations of Deep Learning
course volume CP
-
ECTS credits
6.00
to be declared
yes
fully online course
not
assessment form
Examination
teaching semester
autumn
language of instruction
Estonian
English
Study programmes that contain the course
code of the study programme version
course compulsory
IAIB25/25
no
Structural units teaching the course
IT - Department of Software Science
Course description link
Timetable link
View the timetable
Version:
VERSION SPECIFIC DATA
course aims in Estonian
Tänapäevased tehisintellekti (TI) lahendused põhinevad suures osas masinõppel ja sügavatel närvivõrkudel, ehk süvaõppel. Aine eesmärk on omandada süvaõppe matemaatilised ja algoritmilised alused, mis aitavad mõista, kuidas TI algoritme tõhusalt rakendada. Aine valmistab üliõpilase ette nii tööks masinõppe insenerina kui ka edasiseks akadeemiliseks arenguks TI ja masinõppe valdkonnas.
course aims in English
Modern artificial intelligence (AI) solutions are mainly based on machine learning and deep neural networks, or deep learning. This course will teach the mathematical and algorithmic foundations of deep learning, which will help the student to implement and use AI algorithms efficiently. The course will prepare the student for working as a machine learning engineer and for further academic studies of AI and machine learning.
learning outcomes in the course in Est.
Õppaine läbinud üliõpilane:
- selgitab süvaõppe seoseid ja erinevusi teiste tehisintellekti algoritmidega, süvaõppe tõenäosuslikke aluseid ja masinõppe teoreetilisi aluseid;
- mõõdab süvaõppe algoritmide tulemusi, efektiivsust ja kallutatust ning selgitab andmete ja algoritmide mõju nendele;
- selgitab süvaõppe algoritmide piiranguid ja hindab nende vajadusi, nagu andmemahud, inimtööjõud ja arvutusressurss;
- selgitab närvivõrkude tööpõhimõtteid;
- ehitab süvaõppe mudeleid erinevate masinõppe ülesannete lahendamiseks.
learning outcomes in the course in Eng.
After completing this course, the student:
- explains the similarities and differences between deep learning and other AI algorithms, probabilistic foundations of deep learning and the theoretical principles of machine learning;
- measures the results, performance and bias of deep learning algorithms and explains the impact of data and algorithms on these measurements;
- explains the limitations of deep learning and evaluate the data, human resource and compute needs;
- explains the working principles of neural networks;
- builds deep learning models for different machine learning problems.
brief description of the course in Estonian
Selles õppeaines sharjutatakse erinevate süvaõppe mudelite ehitamist. Õppetöös kasutatakse Pytorch raamistikku ja on vajalik programmeerimiskeele Python oskus. Harjutuste käigus tehakse katseid, mille eesmärk on närvivõrkude tööpõhimõtete uurimine, hindamismeetodite omandamine ja andmete ja algoritmide mõju hindamine. Lisaks on väiksemad harjutused Moodle'is või pliiatsi ja paberiga, et õppida matemaatilisi ja algoritmilisi aluseid.
brief description of the course in English
During the course students will practice building different deep learning models. Pytorch and the Python programming language will be used. The practical work includes experiments with the goal of studying the principles of neural networks, learning evaluation methods and evaluating the impact of data and algorithms. There will be smaller exercises in Moodle or with pen and paper to learn the mathematical and algorithmic principles of deep learning.
type of assessment in Estonian
-
type of assessment in English
-
independent study in Estonian
-
independent study in English
-
study literature
Goodfellow, Ian. "Deep learning." (2016). https://www.deeplearningbook.org/

Poole, David L., and Alan K. Mackworth. "Artificial Intelligence: Foundations of Computational Agents." (2023). https://artint.info/

Murphy, Kevin P. Probabilistic machine learning: an introduction. MIT press, 2022. https://probml.github.io/pml-book/book1.html
study forms and load
daytime study: weekly hours
4.0
session-based study work load (in a semester):
lectures
2.0
lectures
-
practices
2.0
practices
-
exercises
0.0
exercises
-
lecturer in charge
-
LECTURER SYLLABUS INFO
semester of studies
teaching lecturer / unit
language of instruction
Extended syllabus
Course-teacher pairs of the corresponding version are missing!
Course description in Estonian
Course description in English