SECTION I: GENERAL INFORMATION ABOUT THE COURSE |
Course Code | Course Name | Year | Semester | Theoretical | Practical | Credit | ECTS |
70619MEEOS-CME0297 | Neural Networks and Deep Learning | 1 | Spring | 3 | 0 | 3 | 6 |
Course Type : | Departmental Elective |
Cycle: | Master TQF-HE:7. Master`s Degree QF-EHEA:Second Cycle EQF-LLL:7. Master`s Degree |
Language of Instruction: | English |
Prerequisities and Co-requisities: | N/A |
Mode of Delivery: | |
Name of Coordinator: | Öğretim Görevlisi Dr. ENVER AKBACAK |
Dersin Öğretim Eleman(lar)ı: |
Öğretim Görevlisi Dr. ENVER AKBACAK |
Dersin Kategorisi: |
SECTION II: INTRODUCTION TO THE COURSE |
Course Objectives: | 1. To familiarize students with Deep Learning Fundamentals. 2. To Introduce concepts for image, video and text recognition. 3. To teach students featured deep learning practices by a project. |
Course Content: | Fundamentals What is deep learning, layers, learning, wieghts, loss functions, optimizers, CPU, GPU, TPU. Neural Networks Perceptrons, sigmoid neurons, learning with gradient descent and momentum based gradient descent. Neural Networks Back propagation. QUIZ Neural Networks Cost Functions, cross entropy, softmax, regularization, wieght initialization, early stopping, batch size, tanh activation, dropout, normalization, relu layers, pooling layers. Mathematical fundamentals of Neural Networks QUIZ Getting Started with Neural Networks Fundamentals of Deep Learning Supervised, unsupervised, selfsupervised and reinforcement learnings, train/validation/test splits allocations, vanishing gradient descent problem, overfitting and underfitting. Convolutional Neural Networks Fundamentals Pretrained models Fine-tuning Convolutional Neural Networks Feature extraction Python generators Visualizing intermediate activations and filters Class activation maps Encoder – Decoder Models Recurrent Neural Networks LSTMs, Combining CNN-LSTM models Video Processing 3D CNN, Keras functional API, callbacks Project Presentations Final Exam |
Knowledge (Described as Theoritical and/or Factual Knowledge.) | ||
Skills (Describe as Cognitive and/or Practical Skills.) | ||
Competences (Described as "Ability of the learner to apply knowledge and skills autonomously with responsibility", "Learning to learn"," Communication and social" and "Field specific" competences.) |
Week | Subject | ||
Related Preparation | Further Study | ||
1) | Fundamentals What is deep learning, layers, learning, wieghts, loss functions, optimizers, CPU, GPU, TPU. | Fundamentals What is deep learning, layers, learning, wieghts, loss functions, optimizers, CPU, GPU, TPU. | |
2) | Neural Networks Perceptrons, sigmoid neurons, learning with gradient descent and momentum based gradient descent. | ||
3) | Neural Networks Back propagation. | ||
4) | Neural Networks Cost Functions, cross entropy, softmax, regularization, wieght initialization, early stopping, batch size, tanh activation, dropout, normalization, relu layers, pooling layers. | ||
5) | Mathematical fundamentals of Neural Networks | ||
6) | Getting Started with Neural Networks | ||
7) | Fundamentals of Deep Learning Supervised, unsupervised, selfsupervised and reinforcement learnings, train/validation/test splits allocations, vanishing gradient descent problem, overfitting and underfitting. | ||
8) | MidTerm Exam | ||
9) | Convolutional Neural Networks Fundamentals Pretrained models Fine-tuning | ||
10) | Convolutional Neural Networks Feature extraction Python generators Visualizing intermediate activations and filters Class activation maps | ||
11) | Encoder – Decoder Models | ||
12) | Recurrent Neural Networks LSTMs, Combining CNN-LSTM models | ||
13) | Video Processing 3D CNN, Keras functional API, callbacks | ||
14) | Project Presentations |
Course Notes / Textbooks: | |
References: | http://neuralnetworksanddeeplearning.com/ Deep Learning with Python FRANÇOIS CHOLLET |
SECTION III: RELATIONSHIP BETWEEN COURSE UNIT AND COURSE LEARNING OUTCOMES (CLOs) |
CLOs/PLOs | KPLO 1 | KPLO 2 | KPLO 3 | KPLO 4 | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | 1 | 1 | 2 | 3 | 4 | 5 | 1 | 2 | 3 | 4 | 5 | 6 |
No Effect | 1 Lowest | 2 Low | 3 Average | 4 High | 5 Highest |
SECTION IV: TEACHING-LEARNING & ASSESMENT-EVALUATION METHODS OF THE COURSE |
Lectures | |
Discussion | |
Case Study | |
Problem Solving | |
Demonstration | |
Views | |
Laboratory | |
Reading | |
Homework | |
Project Preparation | |
Thesis Preparation | |
Peer Education | |
Seminar | |
Technical Visit | |
Course Conference | |
Brain Storming | |
Questions Answers | |
Individual and Group Work | |
Role Playing-Animation-Improvisation | |
Active Participation in Class |
Midterm | |
Presentation | |
Final Exam | |
Quiz | |
Report Evaluation | |
Homework Evaluation | |
Oral Exam | |
Thesis Defense | |
Jury Evaluation | |
Practice Exam | |
Evaluation of Implementation Training in the Workplace | |
Active Participation in Class | |
Participation in Discussions |
LEARNING & TEACHING METHODS | ASSESMENT & EVALUATION METHODS | ||||||||||||||||||||
-Lectures | -Midterm | ||||||||||||||||||||
-Discussion | -Presentation | ||||||||||||||||||||
-Case Study | -Final Exam | ||||||||||||||||||||
-Problem Solving | -Quiz | ||||||||||||||||||||
-Demonstration | -Report Evaluation | ||||||||||||||||||||
-Views | -Homework Evaluation | ||||||||||||||||||||
-Laboratory | -Oral Exam | ||||||||||||||||||||
-Reading | -Thesis Defense | ||||||||||||||||||||
-Homework | -Jury Evaluation | ||||||||||||||||||||
-Project Preparation | -Practice Exam | ||||||||||||||||||||
-Thesis Preparation | -Evaluation of Implementation Training in the Workplace | ||||||||||||||||||||
-Peer Education | -Active Participation in Class | ||||||||||||||||||||
-Seminar | - Participation in Discussions | ||||||||||||||||||||
-Technical Visit | |||||||||||||||||||||
-Course Conference | |||||||||||||||||||||
-Brain Storming | |||||||||||||||||||||
-Questions Answers | |||||||||||||||||||||
-Individual and Group Work | |||||||||||||||||||||
-Role Playing-Animation-Improvisation | |||||||||||||||||||||
-Active Participation in Class |
Measurement and Evaluation Methods | # of practice per semester | Level of Contribution |
Quizzes | 2 | % 30.00 |
Midterms | 1 | % 20.00 |
Semester Final Exam | 1 | % 50.00 |
Total | % 100 | |
PERCENTAGE OF SEMESTER WORK | % 50 | |
PERCENTAGE OF FINAL WORK | % 50 | |
Total | % 100 |
SECTION V: WORKLOAD & ECTS CREDITS ALLOCATED FOR THE COURSE |
WORKLOAD OF TEACHING & LEARNING ACTIVITIES | |||
Teaching & Learning Activities | # of Activities per semester | Duration (hour) | Total Workload |
Course | 0 | 0 | 0 |
Laboratory | 0 | 0 | 0 |
Application | 0 | 0 | 0 |
Special Course Internship (Work Placement) | 0 | 0 | 0 |
Field Work | 0 | 0 | 0 |
Study Hours Out of Class | 0 | 0 | 0 |
Presentations / Seminar | 1 | 0 | 0 |
Project | 1 | 0 | 0 |
Homework Assignments | 0 | 0 | 0 |
Total Workload of Teaching & Learning Activities | - | - | 0 |
WORKLOAD OF ASSESMENT & EVALUATION ACTIVITIES | |||
Assesment & Evaluation Activities | # of Activities per semester | Duration (hour) | Total Workload |
Quizzes | 2 | 2 | 4 |
Midterms | 1 | 2 | 2 |
Semester Final Exam | 1 | 2 | 2 |
Total Workload of Assesment & Evaluation Activities | - | - | 8 |
TOTAL WORKLOAD (Teaching & Learning + Assesment & Evaluation Activities) | 8 | ||
ECTS CREDITS OF THE COURSE (Total Workload/25.5 h) | 6 |