INTRODUCTION to DEEP LEARNING

AIM

This course is an introduction to deep learning, a branch of machine learning concerned with the development and application of modern neural networks. We will cover a range of topics from basic neural networks, convolutional and recurrent network structures, deep unsupervised learning, and applications to problem domains like computer vision, image processing and natural language processing. The course will introduce training and optimization strategies in deep networks both for supervised and unsupervised learning tasks.

CONTENT

This course contains; Introduction to Machine Learning and Neural Networks,Training Neural Networks,Convolutional Neural Networks (CNNs) ,Network Layers in CNNs ,Deep Learning Hardware and Software,Deep Network Architectures,Deep Learning Strategies,Computer vision applications,Computer Vision and Deep Learning ,Image processing and Deep Learning,Natural Language Processing with Deep Learning,Recurrent Neural Networks and LSTMs,Unsupervised Learning and Generative Modeling,Advanced Applications of Deep Learning .

1. 1

   Design convolutional neural networks for supervised/unsupervised learning

   Taught by: Project Based Learning Model, Simulation Technique, Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

2. 2

   Analyze the effects of hyper-parameters on learning performance

   Taught by: Problem Solving Method, Project Based Learning Model, Simulation Technique, Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

3. 3

   Apply learning techniques for training deep networks

   Taught by: Problem Solving Method, Project Based Learning Model, Simulation Technique, Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

4. 4

   Recognize the applications of deep networks in computer vision, image processing and natural language processing

   Taught by: Project Based Learning Model, Simulation Technique, Experiential Learning, Lecture Method · Assessed by: Homework, Project Task

5. 5

   Use current software and hardware tools for deep learning

   Taught by: Project Based Learning Model, Simulation Technique, Experiential Learning, Lecture Method · Assessed by: Homework, Project Task

WEEKLY PLAN

1. WEEK 1

   Introduction to Machine Learning and Neural Networks

2. WEEK 2

   Training Neural Networks

3. WEEK 3

   Convolutional Neural Networks (CNNs)

4. WEEK 4

   Network Layers in CNNs

5. WEEK 5

   Deep Learning Hardware and Software

6. WEEK 6

   Deep Network Architectures

7. WEEK 7

   Deep Learning Strategies

8. WEEK 8

   Computer vision applications

9. WEEK 9

   Computer Vision and Deep Learning

10. WEEK 10

    Image processing and Deep Learning

11. WEEK 11

    Natural Language Processing with Deep Learning

12. WEEK 12

    Recurrent Neural Networks and LSTMs

13. WEEK 13

    Unsupervised Learning and Generative Modeling

14. WEEK 14

    Advanced Applications of Deep Learning

ASSESSMENT

• Rate of Midterm Exam to Success30%
• Rate of Final Exam to Success70%

WORKLOAD

READING

• Deep Learning, I. Goodfellow, Y. Bengio and A. Courville , MIT Press, http://www.deeplearningbook.org , 2016.
• Machine Learning Yearning, Andrew Ng, http://www.mlyearning.org/, Intel® AI Academy Deep Learning 501 https://software.intel.com/en-us/ai-academy/students/kits/deep-learning-501

TEACHING STAFF

• Prof.Dr. Bahadır Kürşat GÜNTÜRKCOORDINATOR
• Assist.Prof. Ahmet KAPLAN