DEEP LEARNING

BİL635

Course Code: BİL635
Semester: -
Theory+Practice: 3 + 0
ECTS: 10

Course Type

Elective Course

Course Level

Doctorate Of Science

Year of Study

Semester

ECTS

Name of Lecturer(s)

Professor Mustafa Sert

Learning Outcomes

At the end of this course, the students;

Know deep learning methods such as convolutional neural networks, deep Boltzmann machines, and autoencoders.
Know how to design deep architectures for specific problems.
Know training and testing of deep neural networks.

Mode of Delivery

Face to face

Prerequisites

Recommended Optional Programme Components

BIL535 - Introduction to Machine Learning

Course Description

Course Contents

WEEK	TOPICS
1^st Week	Machine learning basics and applications
2^nd Week	Overview of artificial neural networks
3^rd Week	Multilayer perceptron
4^th Week	Training deep networks
5^th Week	Convolutional neural networks
6^th Week	Convolutional neural networks
7^th Week	Recurrent neural networks
8^th Week	Midterm
9^th Week	Deep generative models
10^th Week	Deep generative models
11^th Week	Deep reinforcement learning
12^th Week	Deep reinforcement learning
13^th Week	Recent research topics and applications on audio-visual and language understanding.
14^th Week	Recent research topics and applications on audio-visual and language understanding.

Recommended or Required Reading

1. Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016
2. K. P. Murphy. Machine Learning: A Probabilistic Perspective, MIT Press, 2012.
3. Tom Mitchell, \Machine Learning", McGraw-Hill, (1997).

Planned Learning Activities and Teaching Methods

Lecture
Questions/Answers
Problem Solving
Presentation

Assessment Methods and Criteria

	Quantity	Percentage (%)
Mid-term	1	30
Assignment	1	30
Total(%)		60
Contribution of In-term Studies to Overall Grade(%)		60
Contribution of Final Examination to Overall Grade(%)		40
Total(%)		100

ECTS Allocated Based on Student Workload

Activities	Quantity	Duration (Hour)	Total Workload (Hour)
Midterm exam	1	2	2
Preparation for Quiz
Individual or group work
Preparation for Final exam
Course hours	14	3	42
Preparation for Midterm exam	1	30	30
Laboratory (including preparation)
Final exam
Homework	2	40	80
Project	1	150	150
Total Work Load			304
Total Work Load / 30 (h)			10.13
ECTS Credit of the Course			10

Language of Instruction

Turkish

Work Placement(s)

Programme Qualifications / Learning Outcomes

	LO1	LO2	LO3
K1	X	X
K2	X	X
K3			X
K4	X	X	X
K5		X
K6		X
K7
K8
K9
K10		X
K11
K12