ISB304 Introduction to Artificial Neural Networks

3 ECTS - 2-0 Duration (T+A)- 6. Semester- 2 National Credit
Information About Course

Information
Goal, Content & Resources
Course Learning Outcomes
Relation with Program Learning Outcome
Week Plan
Student Workload - ECTS

Information

Code ISB304
Name Introduction to Artificial Neural Networks
Semester 6. Semester
Duration (T+A) 2-0 (T-A) (17 Week)
ECTS 3 ECTS
National Credit 2 National Credit
Teaching Language Türkçe
Level Lisans Dersi
Type Normal
Mode of study Yüz Yüze Öğretim
Catalog Information Coordinator Prof. Dr. GÜLESEN ÜSTÜNDAĞ ŞİRAY


Course Goal

The aim of this course is to introduce the artificial neural network and show how to analyze data using artificial neural network for students.

Course Content

Introduction, Basics of ANN, Learning Processes, Some Optimization Algorithms, Single-Layer Perceptrons, Multilayer Perceptrons

Course Precondition

None

Resources

Introduction to Machine Learning (2010), 2nd edition,The MIT Press. Ethem ALPAYDIN Yapay Zeka Uygulamaları, Seçkin Yayıncılık. Prof. Dr. Çetin ELMAS Yapay Sinir Ağları, Nobel Yayıncılık. Prof. Dr. Erol EĞRİOĞLU, Prof.Dr. Ufuk YOLCU, Prof.Dr. Eren BAŞ Yapay Sinir Ağları, Papatya Yayıncılık. Prof.Dr. Ercan ÖZTEMEL

Notes

Internet


Course Learning Outcomes

Order Course Learning Outcomes
LO01 Knows the basics of artificial neural networks (ANN).
LO02 Defines the components of ANN.
LO03 Builds an artificial neural network.
LO04 Compares the effects of different activation functions on ANN.
LO05 Distinguishes between single-layer and multi-layer perceptrons.
LO06 Uses difference optimization algorithms to build an ANN.
LO07 Performs data analysis with ANN.


Relation with Program Learning Outcome

Order Type Program Learning Outcomes Level
PLO01 Bilgi - Kuramsal, Olgusal Explain the essence fundamentals and concepts in the field of Probability, Statistics and Mathematics
PLO02 Bilgi - Kuramsal, Olgusal Emphasize the importance of Statistics in life 4
PLO03 Bilgi - Kuramsal, Olgusal Define basic principles and concepts in the field of Law and Economics
PLO04 Bilgi - Kuramsal, Olgusal Produce numeric and statistical solutions in order to overcome the problems 5
PLO05 Bilgi - Kuramsal, Olgusal Use proper methods and techniques to gather and/or to arrange the data 4
PLO06 Bilgi - Kuramsal, Olgusal Utilize computer systems and softwares 4
PLO07 Bilgi - Kuramsal, Olgusal Construct the model, solve and interpret the results by using mathematical and statistical tehniques for the problems that include random events 5
PLO08 Bilgi - Kuramsal, Olgusal Apply the statistical analyze methods 5
PLO09 Bilgi - Kuramsal, Olgusal Make statistical inference(estimation, hypothesis tests etc.) 5
PLO10 Bilgi - Kuramsal, Olgusal Generate solutions for the problems in other disciplines by using statistical techniques 5
PLO11 Bilgi - Kuramsal, Olgusal Discover the visual, database and web programming techniques and posses the ability of writing programme 4
PLO12 Bilgi - Kuramsal, Olgusal Construct a model and analyze it by using statistical packages 4
PLO13 Beceriler - Bilişsel, Uygulamalı Distinguish the difference between the statistical methods 2
PLO14 Beceriler - Bilişsel, Uygulamalı Be aware of the interaction between the disciplines related to statistics 5
PLO15 Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği Make oral and visual presentation for the results of statistical methods
PLO16 Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği Have capability on effective and productive work in a group and individually
PLO17 Yetkinlikler - Bağımsız Çalışabilme ve Sorumluluk Alabilme Yetkinliği Professional development in accordance with their interests and abilities, as well as the scientific, cultural, artistic and social fields, constantly improve themselves by identifying training needs
PLO18 Yetkinlikler - Öğrenme Yetkinliği Develop scientific and ethical values in the fields of statistics-and scientific data collection


Week Plan

Week Topic Preparation Methods
1 Introduction to ANN, General usage areas, advantages and disadvantages of ANN Source reading Öğretim Yöntemleri:
Anlatım, Soru-Cevap
2 Components of ANN Source reading Öğretim Yöntemleri:
Soru-Cevap, Alıştırma ve Uygulama, Anlatım
3 Single Layer Perceptrons Source reading Öğretim Yöntemleri:
Anlatım, Soru-Cevap
4 Activation Functions Source reading Öğretim Yöntemleri:
Anlatım, Soru-Cevap, Problem Çözme, Alıştırma ve Uygulama
5 Learning Algorithms Source reading Öğretim Yöntemleri:
Anlatım, Soru-Cevap, Alıştırma ve Uygulama
6 Optimization Algorithms Source reading Öğretim Yöntemleri:
Anlatım, Alıştırma ve Uygulama, Problem Çözme
7 Optimization Algorithms II Source reading Öğretim Yöntemleri:
Anlatım, Problem Çözme
8 Mid-Term Exam Review the topics discussed in the lecture notes and sources Ölçme Yöntemleri:
Yazılı Sınav
9 Multi Layer Perceptrons Source reading Öğretim Yöntemleri:
Anlatım, Alıştırma ve Uygulama, Problem Çözme
10 Multi Layer Perceptrons II Source reading Öğretim Yöntemleri:
Anlatım, Alıştırma ve Uygulama, Problem Çözme
11 Supervised Learning Source reading Öğretim Yöntemleri:
Anlatım, Alıştırma ve Uygulama, Problem Çözme
12 Unsupervised Learning Source reading Öğretim Yöntemleri:
Anlatım, Alıştırma ve Uygulama, Problem Çözme
13 ANN Applications with Matlab Doing applications in MATLAB Öğretim Yöntemleri:
Alıştırma ve Uygulama
14 ANN Applications with Matlab II Doing applications in MATLAB Öğretim Yöntemleri:
Alıştırma ve Uygulama
15 ANN Applications with Matlab III Doing applications in MATLAB Öğretim Yöntemleri:
Alıştırma ve Uygulama
16 Term Exams Review the topics discussed in the lecture notes and sources Ölçme Yöntemleri:
Yazılı Sınav
17 Term Exams Review the topics discussed in the lecture notes and sources Ölçme Yöntemleri:
Yazılı Sınav


Student Workload - ECTS

Works Number Time (Hour) Workload (Hour)
Course Related Works
Class Time (Exam weeks are excluded) 14 2 28
Out of Class Study (Preliminary Work, Practice) 14 1 14
Assesment Related Works
Homeworks, Projects, Others 1 7 7
Mid-term Exams (Written, Oral, etc.) 1 7 7
Final Exam 1 12 12
Total Workload (Hour) 68
Total Workload / 25 (h) 2,72
ECTS 3 ECTS