Biyomedikal Mühendisliği

CE 470 | Ders Tanıtım Bilgileri

Dersin Adı

Introduction to Neural Networks

Kodu	Yarıyıl	Teori (saat/hafta)	Uygulama/Lab (saat/hafta)	Yerel Kredi	AKTS
CE 470	FALL	3	0	3	5

Ön-Koşul(lar)	None
Dersin Dili	English
Dersin Türü	ELECTIVE_COURSE
Dersin Düzeyi	Lisans
Dersin Veriliş Şekli	Face-To-Face
Dersin Öğretim Yöntem ve Teknikleri	Problem Solving Case Study Lecture / Presentation
Ulusal Meslek Sınıflandırma Kodu	-
Dersin Koordinatörü	Dr. Öğr. Üyesi Kaya Oğuz
Öğretim Eleman(lar)ı	-
Yardımcı(ları)	-

Dersin Amacı

This course will introduce the fundamental principles and algorithms of Artificial Neural Network (ANN) systems. The course will cover many subjects including basic neuron model, simple perceptron, adaptive linear element, Least Mean Square (LMS) algorithm, Multi Layer Perceptron (MLP), Back Propagation (BP) learning algorithm, Radial Basis Function (RBF) networks, Self Organizing Maps (SOM) and Learning Vector Quantization (LVQ), Support Vector Machines (SVMs), Continuous time and discrete time Hopfield networks, classification techniques, pattern recognition, signal processing and control applications.

Öğrenme Çıktıları

Bu dersi başarıyla tamamlayabilen öğrenciler;

Ad	Açıklama	PC Alt	* Katkı Düzeyi
Ad	Açıklama	PC Alt	1	2	3	4	5
LO5	Implement basic ANN models and algorithms using Matlab and its Neural Network Toolbox.			X
LO4	Evaluate the practical considerations in applying ANNs to real classification, pattern recognition, signal processing and control problems,						X
LO3	Explain the principles of supervised and unsupervised learning, and generalization ability,					X
LO2	Use the most common ANN architectures and their learning algorithms for a specific application,						X
LO1	Describe basic artificial neural network models,					X

Ders Tanımı

The following topics will be included in the course: The main neural network architectures and learning algorithms, perceptrons and the LMS algorithm, back propagation learning, radial basis function networks, support vector machines, Kohonen’s self organizing feature maps, Hopfield networks, artificial neural networks for signal processing, pattern recognition and control.

Dersin İlişkili Olduğu Sürdürülebilir Kalkınma Amaçları

Dersin Kategorisi	Temel Ders
	Uzmanlık/Alan Dersleri	X
	Destek Dersleri
	İletişim ve Yönetim Becerileri Dersleri
	Aktarılabilir Beceri Dersleri

HAFTALIK KONULAR VE İLGİLİ ÖN HAZIRLIK ÇALIŞMALARI

Hafta	Konular	Ön Hazırlık	Öğrenme Çıktısı
1	Biological motivation. Historical remarks on artificial neural networks. Applications of artificial neural networks. A taxonomy of artificial neural network models and learning algorithms.	Introduction. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes.	LO1
2	General artificial neuron model. Discretevalued perceptron model, threshold logic and their limitations. Discretetime (dynamical) Hopfield networks. Hebb’s rule. Connection wieght matrix as an outer product of memory patterns.	Chapter 1. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes.	LO1
3	Supervised learning. Perceptron learning algorithm. Adaptive linear element. Supervised learning as output error minimization problem. Gradient descent algorithm for minimization. Least mean square rule.	Chapter 2. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes.	LO1
4	Single layer, continuous valued perceptron. Nonlinear (sigmoidal) activation function. Delta rule. Batch mode and pattern mode gradient descent algorithms. Convergence conditions for deterministic and stochastic gradient descent algorithms.	Chapter 3. Chapter 4: Sections 4.1, 4.2, 4.16. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes.	LO1
5	Multi layer perceptron as universal approximator. Function representation and approximation problems. Backpropagation Learning. Local minima problem. Overtraining.	Chapter 4: Sections 4.4, 4.5, 4.8, 4.10, 4.12. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761. Lecture Notes.	LO2
6	Midterm Exam I		-
7	Batch and pattern mode training. Training set versus test set. Overfitting problem. General practices for network training and testing. Signal processing and pattern recognition applications of multilayer perceptrons.	Chapter 4: Sections 4.3, 4.10., 4.11, 4.13, 4.14, 4.15, 4.19, 4.20. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761.	LO3
8	Radial Basis Function (RBF) network. Backpropagation learning for determining linear weights, centers and widths parameters of RBF networks. Random selection of centers. Input versus input-output clustering for center and width determination. Regularization theory, mixture of Gaussian (conditional probability density function) model and neurofuzzy connections of RBF networks.	Chapter 5. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761	LO2
9	Parametric versus nonparametric methods for data representation. Unsupervised learning as a vector quantization problem. Competitive networks. Winner takes all networks. Kohonen’s self organizing feature map. Clustering.	Chapter 9. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761.	LO4
10	Signal processing applications of artificial neural networks. Principal component analysis. Data compression and reduction. Image and 1D signal compression and transformation applications of artificial neural networks.	Chapter 8. S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761	LO3
11	Midterm Exam II		-
12	Pattern recognition applications of artificial neural networks. Artificial neural networks for feature extraction. Nonlinear feature mapping. Data fusion. Artificial neural networks as classifiers. Image and speech recognition applications.	Sections 1.4,1.5., 3.11, 4.7, 5.8, 6.7, S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761.	LO3
13	Implementation of artificial neural networks models and associated learning algorithms for signal processing, pattern recognition and control in MATLAB numerical software environment.	L. Fausett, Fundamentals of Neural Networks, Chapter 6, Prentice Hall, ISBN-13: 978-0133341867	LO5
14	Cumulative review of artificial neural networks models, learning algorithms and their applications.	S. Haykin, Neural Networks and Learning Machines, Pearson Education, 3rd Ed., 2009, ISBN13 9780131293762 ISBN10 0131293761.	LO4
15	Review of the Semester		-
16	Review of the Semester		-

Ders Kitabı	S. Haykin Neural Networks and Learning Machines Pearson Education 3rd Ed. 2009 ISBN13 9780131293762 ISBN10 0131293761
Önerilen Okumalar/Materyaller	J. M. Zurada Int. To Artificial Neural Systems West Publishing Company 1992 ISBN 053495460X 9780534954604. L. Fausett Fundamentals of Neural Networks Prentice Hall ISBN-13: 978-0133341867

DEĞERLENDİRME ÖLÇÜTLERİ

Yarıyıl Aktiviteleri	Sayı	Katkı Payı %	LO5	LO4	LO3	LO2	LO1
Ara Sınav	2	50		X	X	X	X
Proje	1	30	X	X	X	X	X
Ödev	1	20	X			X
Toplam	4	100

AKTS / İŞ YÜKÜ TABLOSU

Yarıyıl Aktiviteleri	Sayı	Süre (Saat)	İş Yükü
Katılım	-	-	-
Teorik Ders Saati	16	3	48
Laboratuvar / Uygulama Ders Saati	-	-	-
Sınıf Dışı Ders Çalışması	14	3	42
Arazi Çalışması	-	-	-
Küçük Sınav / Stüdyo Kritiği	-	-	-
Portfolyo	-	-	-
Ödev	1	10	10
Sunum / Jüri Önünde Sunum	-	-	-
Proje	1	20	20
Seminer/Çalıştay	-	-	-
Sözlü Sınav	-	-	-
Ara Sınavlar	2	15	30
Final Sınavı	-	-	-
		Toplam	150