NEURAL NETWORKS AND DEEP LEARNING
- Course
- DASC488 - NEURAL NETWORKS AND DEEP LEARNING
- Department
- Data Science - English - Undergraduate
- Course Type
- Course
- Status
- Required
- Language
- English
- Credit
- 3
- ECTS
- 6
- T+P+L
- 3 + 0 + 1
- Course Coordinator(s)
- Prof. Dr. Tolgay KARANFİLLER
- Prerequisite
- -
Course Description
In this course Artificial Neural Network (ANN), which is a mathematical paradigm imitating biological neural network for reasoning and problem solving is covered. With focus on practice, the course cover ANN models for various real-world applications and offers a hands-on introduction to deep learning tools and techniques. Students do not need to have an extensive math background to understand this course. The course covers McCulloch-Pitts model and basic neural network models, multilayer perceptron, associative memory, self-organizing feature maps, recurrent neural networks, etc. and reviews applications of these models to various types of data. Upon completion of this course, students will gain a broad understanding of the context of neural networks and deep learning, the data demands of deep learning and the parameters for neural networks.
NEURAL NETWORKS AND DEEP LEARNING
Evaluation Tools (Active Term)
| Item | Type | Weight (%) |
|---|---|---|
| Kısa Sınav 1 | Quiz | 15 |
| Kısa Sınav 2 | Quiz | 15 |
| Vize | Midterm | 30 |
| Final | Final | 40 |
| Total | 100 | |
Course Syllabus
| Week | Topic |
|---|---|
| Week 1 | Introduction to Artificial Neural Networks |
| Week 2 | Basic Neuron Models — The McCulloch–Pitts Model |
| Week 3 | The Perceptron and Its Learning Rule |
| Week 4 | ADALINE / Delta Rule and Its Limitations |
| Week 5 | The Multilayer Perceptron (MLP) |
| Week 6 | Training the MLP and First Hands-On Model |
| Week 7 | Deep Learning Tools and Techniques |
| Week 8 | Midterm Exam Week |
| Week 9 | Midterm Exam Week |
| Week 10 | Convolutional Neural Networks (CNN) |
| Week 11 | Recurrent Neural Networks (RNN) |
| Week 12 | Advanced Sequence Modeling with LSTM / GRU |
| Week 13 | Associative Memory — Hopfield Networks |
| Week 14 | Self-Organizing Feature Maps (SOM / Kohonen) |
| Week 15 | Week 13: Applications, Data Requirements, and Course Review |
Reference Books & Course Materials
- 01 Neural Networks and Deep Learning: A Textbook (2. Baskı, 2023) Charu C. Aggarwal · Springer
- 02 Deep Learning with Python (2. Baskı, 2021) François Chollet (Keras'ın yaratıcısı) · Manning
- 03 Grokking Deep Learning (2019,) Andrew Trask · Manning
Learning Outcomes
No learning outcomes have been defined.
Program Outcomes
- P01 Apply data science principles and techniques to challenges in real life situations, and effectively communicate their solutions.
- P02 Identify and implement data analysis methodologies based on theoretical ideas, ethical code, and in-depth knowledge of the underlying data.
- P03 Analyze the guiding concepts and assessment procedures for information analysis in real-life applications.
- P04 Design and apply relevant data analysis models to find obscure solutions to business-related problems.
- P05 Utilize modern computing techniques to handle real-world problems characterized by massive amounts of data, such as parallel and distributed computing and machine learning.
- P06 Configure and administer the software tools required to efficiently produce usable information from any size of structured and unstructured datasets.
- P07 Administer or manage data science tools and techniques to organize and complete projects aimed at gaining useful insight from complex data.
- P08 Think critically and imaginatively, conceiving real-world issues from several angles, and work well in a variety of teams to solve issues cooperatively.
- P09 Be able to effectively integrate data‐based solutions into the user environment and help non-technical professionals in exploring, visualizing, and using these solutions
- P10 Understand their obligations under professional and ethical standards in relation to matters like data ownership and citation, data security and sensitivity and the privacy implications of data analysis.
Po-Lo Matrix
The PO-LO matrix has not been populated yet.