TÜRKÇE
ENGLISH
Information
| Unit | FACULTY OF ENGINEERING |
| COMPUTER ENGINEERING PR. (ENGLISH) | |
| Code | CEN402 |
| Name | Artificial Neural Networks |
| Term | 2019-2020 Academic Year |
| Semester | 8. Semester |
| Duration (T+A) | 3-0 (T-A) (17 Week) |
| ECTS | 6 ECTS |
| National Credit | 3 National Credit |
| Teaching Language | İngilizce |
| Level | Lisans Dersi |
| Type | Normal |
| Label | E Elective |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | |
| Course Instructor |
The current term course schedule has not been prepared yet. Previous term groups and teaching staff are shown.
|
Course Goal / Objective
To gain the ability to use the artificial neural networks based on mathematical models of biological neural cell for modelling and solving engineering problems.
Course Content
History of Neural Networks, Fundamental Neural Networks, Statistical Pattern Recognition, Classification, Single-Layer Networks, Multi-Layer Networks-Backpropagation Model, Radial Basis Function, Error Functions.
Course Precondition
Yok
Resources
Notes
Neural Networks, S. Haykin, Prenctice Hall, Second Edition, 1999.
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Use of mathematical base model for artificial neural network |
| LO02 | Understand the necessary mathematical base for neural networks |
| LO03 | Implementing multilayer perceptron neural network on software and apply it to real life problems |
| LO04 | Developing radial basis function |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | - | Has capability in the fields of mathematics, science and computer that form the foundations of engineering | 5 |
| PLO02 | - | Identifies, formulates, and solves engineering problems, selects and applies appropriate analytical methods and modeling techniques, | 5 |
| PLO03 | - | Analyzes a system, its component, or process and designs under realistic constraints to meet the desired requirements,gains the ability to apply the methods of modern design accordingly. | 4 |
| PLO04 | - | Ability to use modern techniques and tools necessary for engineering practice and information technologies effectively. | 3 |
| PLO05 | - | Ability to design and to conduct experiments, to collect data, to analyze and to interpret results | 0 |
| PLO06 | - | Has ability to work effectively as an individual and in multi-disciplinary teams, take sresponsibility and builds self-confidence | 0 |
| PLO07 | - | Can access information,gains the ability to do resource research and uses information resources | 0 |
| PLO08 | - | Awareness of the requirement of lifelong learning, to follow developments in science and technology and continuous self-renewal ability | 2 |
| PLO09 | - | Ability to communicate effectively orally and in writing, and to read and understand technical publications in at least one foreign language | 0 |
| PLO10 | - | Professional and ethical responsibility, | 0 |
| PLO11 | - | Awareness about project management, workplace practices, employee health, environmental and occupational safety, and the legal implications of engineering applications, | 1 |
| PLO12 | - | Becomes aware of universal and social effects of engineering solutions and applications, entrepreneurship and innovation, and knowledge of contemporary issues | 3 |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Slope reduction and uplift methods and applications for engineering problems | Read the related section of the book | |
| 2 | Biological and artificial nerve cells, neural cell models | Read the related section of the book | |
| 3 | Learning with a teacher algorithms : Perceptron Learning | Read the related section of the book | |
| 4 | Basic network topologies and Multi-layer Perceptron network (MLP) | Read the related section of the book Homework 1 | |
| 5 | Learning error back propagation | Read the related section of the book Homework 2 | |
| 6 | Radial basis function networks | Read the related section of the book | |
| 7 | General Regression Neural Network (GRNN) | Reading the lecture notes | |
| 8 | Mid-Term Exam | Read the related section of the book Homework 3 | |
| 9 | Probabilistic Neural Network (PNN) | Read the related section of the book Homework 4 | |
| 10 | Learning without a teacher and Hamming network | Read the related section of the book Homework 5 | |
| 11 | Mexican hat and MaxNet networks | Read the related section of the book Homework 6 | |
| 12 | Learning Vector Quantization (LVQ) | Read the related section of the book | |
| 13 | Self-Organizing Maps (SOM) | Read the related section of the book | |
| 14 | Adaptive Resonance Theory Neural Networks | Read the related section of the book | |
| 15 | Principal Component Analysis | Read the related section of the book | |
| 16 | Term Exams | Reviewing lecture notes | |
| 17 | Term Exams | Reviewing lecture notes |
Assessment (Exam) Methods and Criteria
Current term shares have not yet been determined. Shares of the previous term are shown.
| Assessment Type | Midterm / Year Impact | End of Term / End of Year Impact |
|---|---|---|
| 1. Midterm Exam | 100 | 40 |
| General Assessment | ||
| Midterm / Year Total | 100 | 40 |
| 1. Final Exam | - | 60 |
| Grand Total | - | 100 |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 14 | 3 | 42 |
| Out of Class Study (Preliminary Work, Practice) | 14 | 5 | 70 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 0 | 0 | 0 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 15 | 15 |
| Final Exam | 1 | 30 | 30 |
| Total Workload (Hour) | 157 | ||
| Total Workload / 25 (h) | 6,28 | ||
| ECTS | 6 ECTS | ||