TÜRKÇE
ENGLISH
Information
| Unit | INSTITUTE OF NATURAL AND APPLIED SCIENCES |
| ELECTRICAL-ELECTRONICS ENGINEERING (MASTER) (WITH THESIS) (ENGLISH) | |
| Code | EE588 |
| Name | Advanced Topics in Neural Networks |
| Term | 2018-2019 Academic Year |
| Term | Spring |
| Duration (T+A) | 3-0 (T-A) (17 Week) |
| ECTS | 6 ECTS |
| National Credit | 3 National Credit |
| Teaching Language | İngilizce |
| Level | Belirsiz |
| Type | Normal |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Doç. Dr. TURGAY İBRİKÇİ |
| Course Instructor |
The current term course schedule has not been prepared yet.
|
Course Goal / Objective
The objective of the Advances Topic in Neural Networks course is to expand on the material covered in the introduction to Neural Networks course (EE589). It focuses on special topics in NN such as exact and approximate inference in graphical models, dimensionality reduction and component analysis methods, latent variable models, models of documents and words, time series models and selected topic from deep neural networks. The course will consist of (each student) presentations and discussions. Students will be evaluated based on their participation in discussions, presentations, and projects that will be a manuscript or a conference paper.
Course Content
Discussion of the results of research, Parameter Optimization Algorithms, Learning and Generalization, Bayesian Techniques, Mixture Models, and Applications of Neural Networks.
Course Precondition
Resources
Notes
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Distinguish definitions of key concepts in Neural Networks analysis, including data of sets and algorithms, subgradients, and learning models |
| LO02 | Fundamentals of Deep Learning |
| LO03 | The students will learn how to structure a scientific presentation in English. |
| LO04 | Evaluate the performance of the Neural Networks learning system |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Learning from Data | Read related topics from articles and books | |
| 2 | Learning features with multilayer neural networks | Read related topics from articles and books | |
| 3 | Graphical models: Bayesian belief networks | Read related topics from articles and books | |
| 4 | Non-linear dimensionality reduction and kernels: eigenmaps, isomaps, locally linear embeddings | Read related topics from articles and books | |
| 5 | Gaussian Processes: classification | Read related topics from articles and books | |
| 6 | Markov decision processes | Read related topics from articles and books | |
| 7 | Deep Learning Theory, Generalization of Neural Nets | Read related topics from articles and books | |
| 8 | Mid-Term Exam | ||
| 9 | Deep Neural Nets: Convolutional neural networks | Read related topics from articles and books | |
| 10 | Deep Neural Nets: Recurrent neural networks | Read related topics from articles and books | |
| 11 | How to write a conference paper | Read related topics from articles and books | |
| 12 | Seminars/Presentations | Read related topics from articles and books | |
| 13 | Seminars/Presentations | Read related topics from articles and books | |
| 14 | Seminars/Presentations | Read related topics from articles and books | |
| 15 | Seminars/Presentations | Read related topics from articles and books | |
| 16 | Term Exams | General Study | |
| 17 | Term Exams | General Study |