EGE UNIVERSITY

FACULTY of ENGINEERING

COMPUTER ENGINEERING DEPARTMENT

 

 

 

 

2020-2021 SPRING SEMESTER

 

 

 

Course

 

435 İŞLEMSEL ZEKA ve DERİN ÖĞRENME
(COMPUTATIONAL INTELLIGENCE and DEEP LEARNING) (3+0)

 

 

Instructor

 

 

Prof. Dr. Aybars UĞUR

 

Course Place

 

Online, Teams

EGE University Computer Engineering Department

 

 

Course Time

 

Wednesday, 9:30 - 12:15

 

 

Assistants

 

 

Arş. Gör. Ensar Arif SAĞBAŞ       

 

Arş. Gör. Ahmet GÜRBÜZ

 

Arş. Gör. Sezercan TANIŞMAN

 

 

 

 

 

 

 

 

 

Learning Outcomes

 

1.     To learn basic concepts of Computational Intelligence and Deep Learning, mathematical and software background; to have ability to apply Computational Intelligence to problems. To recognize the role of Computational Intelligence in computer engineering, computer science and artificial intelligence.

 

2.     To introduce and to learn ability to use popular Computational Intelligence and Deep Learning libraries / tools. To enable to write simple Artificial Intelligence libraries in modern programming platforms (like Java and C#). To Develop Optimization, Prediction, Estimation, Classification and Recognition Projects.

 

3.     To develop Intelligent Software; To recognize that how the computers learn; To make efficient designs.

 

4.     To do research in state-of-the-art subjects of Computational Intelligence and Deep Learning areas; preparing and doing presentation. To gain experience in reading and writing papers in Machine Learning.

 

 

 

 

Aim

 

The goal of the course is to give the students:

 

·       Basic knowledge and practical experience about techniques like Artificial Neural Networks, Deep Learning, Fuzzy Logic, Genetic Algorithms and Swarm Intelligence based on Computational Intelligence and Soft Computing;

 

·       with an understanding of the role of Computational Intelligence in computer engineering, computer science and artificial intelligence.

 

 

Course Contents

 

Computational Intelligence, Artificial Neural Networks, Artificial Neuron, Structure and Basic Elements of ANN, Machine Learning, Supervised, Reinforcement and Unsupervised Learning, Single Layer Perceptons, Multi Layer Perceptrons (MLP), Other Neural Models, Deep Learning, CNN, RNN, LSTM and Autoencoder Models, Application Areas of ANN, Object Recognition, Fuzzy Logic, Genetic Algorithms, Swarm Intelligence.

 

 

Prerequisites

 

Basic knowledge of Probability, Statistics and Calculus.

Java / C# / Python or Matlab programming experience.

 

 

 

 

Textbook

 

 

§  Russell, S.J. And Norvig, P., “Artificial Intelligence : A Modern Approach, Third Edition”, Prentice-Hall, 2009. (AIMA)

 

§  Prof. Dr. Ercan Öztemel,  2012, “Yapay Sinir Ağları”, Papatya Yayıncılık, 232s.

§  Prof. Dr. Çetin Elmas, 2018, "Yapay Zeka Uygulamaları", 4. Baskı, Seçkin Yayıncılık, 479 s.

 

 

Reference Books

 

§  Deep Learning Books

§  https://www.deeplearningbook.org/

§  Deep Learning with Python, François Chollet, 1st edition, Manning Publications.

 

§  Haykin, Simon, 1998, “Neural Networks: A Comprehensive Foundation (2nd Edition)”, Prentice-Hall, 842p

§  Vasif Nabiyev , Yapay Zeka: İnsan – Bilgisayar Etkileşimi, 3. baskı, 752 s., Seçkin, Ankara, 2010.

§  Okyay Kaynak ve M. Önder Efe, “Yapay Sinir Ağları ve Uygulamaları”, Boğaziçi Üniversitesi Yayınevi, 141s.

§  Şeref Sağıroğlu, Erkan Beşdok, Mehmet Erler, 2003, “Mühendislikte Yapay Zeka Uygulamaları - I : Yapay Sinir Ağları”, Ufuk Yayıncılık, 426s.

 

Also Sample Papers will be given.

 

 

Grading

 

 

Dönemiçi Etkinlikler : %40, Dönem Projesi (Proje 2) + Final Sınavı : %60

Pandemi durumuna göre Final Sınavının nota etkisi değiştirilebilir.

 

Proje 1

15 %

Take-Home ve Sınav/Quiz

15 %

Sunum

10 %

Proje 2 (Ara Rapor)

10 %

Proje 2 ve Rapor

25 %

Proje 2 Video

10 %

Final Sınavı

15 %