Information Package / Course Catalogue
| Course Code | : MTK580 |
| Course Type | : Area Elective |
| Couse Group | : Second Cycle (Master's Degree) |
| Education Language | : Turkish |
| Work Placement | : N/A |
| Theory | : 3 |
| Prt. | : 0 |
| Credit | : 3 |
| Lab | : 0 |
| ECTS | : 8 |
Nowadays, the methods of artificial intelligence are widely used in computer science. Artificial neural networks (ANN) are very advantageous in most systems, especially in the systems which have very complex mathematical structures. In this course, the aim is to teach the fundamental ANN subjects and to develop some ANN applications.
Introduction to Artificial Intelligence and Machine Learning. Introduction to Artificial Neural Networks (ANNs). The basic structures of ANNs. Elementary Artificial Neural Networks. Supervised learning. Multilayer Perceptron. Reinforcement learning. Learning Vector Quantization (LVQ). Unsupervised learning. Adaptive Resonance Theory (ART). Recurrent Neural Networks and other networks. Hybrid ANN Models. Neural Network Hardware. Applications of ANN.
| Lec. Rıfat AŞLIYAN |
| 1. | To be able to recognize the artificial neural network (ANN) concepts. |
| 2. | To be able to design ANN with supervised, unsupervised and reinforcement learning. |
| 3. | To be able to design multilayer perceptron, Learning Vector Quantization (LVQ), Adaptive Resonance Theory (ART), Recurrent Neural Networks and other networks. |
| 4. | To be able to develop some applications with ANN. |
| 5. | To be able to gain the skill of interpreting some interrelations among these concepts |
| 1. | Prof. Dr. Ercan Öztemel, Yapay Sinir Ağları (Artificial Neural Networks), Papatya Yayıncılık, 2003. |
| 2. | T. Khana, Foundations of Neural Networks, Addison-Wesley Publishing Comp., 1990. |
| 3. | L. H. Tsoukalas, R. E. Uhrig, Fuzzy and Neural Approaches in Engineering, John Wiley & Sons, Inc. , 1997. |
| Type of Assessment | Count | Percent |
|---|---|---|
| Midterm Examination | 1 | %30 |
| Final Examination | 1 | %70 |
| Activities | Count | Preparation | Time | Total Work Load (hours) |
|---|---|---|---|---|
| Lecture - Theory | 14 | 0 | 3 | 42 |
| Individual Work | 14 | 0 | 4 | 56 |
| Midterm Examination | 1 | 42 | 3 | 45 |
| Final Examination | 1 | 54 | 3 | 57 |
| TOTAL WORKLOAD (hours) | 200 | |||
PÇ-1 | PÇ-2 | PÇ-3 | PÇ-4 | PÇ-5 | PÇ-6 | PÇ-7 | PÇ-8 | PÇ-9 | PÇ-10 | PÇ-11 | PÇ-12 | PÇ-13 | PÇ-14 | PÇ-15 | |
OÇ-1 | 4 | 3 | 2 | 3 | 3 | 2 | |||||||||
OÇ-2 | 5 | 4 | 3 | 4 | 3 | 3 | |||||||||
OÇ-3 | 5 | 4 | 4 | 4 | 4 | 3 | |||||||||
OÇ-4 | 5 | 4 | 4 | 4 | 4 | 3 | |||||||||
OÇ-5 | 5 | 4 | 4 | 4 | 4 | 3 | |||||||||