• HOME
• ABOUT US
  • Name Address
  • General Description
  • Governance
  • Academic Calendar
  • Degree Programmes
  • List of Programmes in English
  • General Admission and Registration Procedures
  • Credit Mobility and Recognition of Prior Learning
  • ECTS Credit Allocation
  • Academic Guidance
  • Contacts
• Degree Programmes
  • Third Cycle Programmes (Doctorate Degree)
  • Second Cycle Programmes (Master's Degree)
  • First Cycle Programmes (Bachelor's Degree)
  • Short Cycle Programmes (Associate's Degree)
• GENERAL INFORMATION FOR STUDENTS
  • Cost of Living
  • Accommodation
  • Meals
  • Medical Facilities
  • Facilities for Disabled Students
  • Insurance
  • Financial Supports
  • Student Affairs Office
  • Practical Information for International Students
  • Language Courses
  • Work Placement Possibilities
  • Sports, Social and Cultural Facilities
  • Student Associations and Clubs
  • About İzmir - Turkey
• INTERNATIONAL RELATIONS
  • International Relations Office
  • Registration Procedures
  • Agreements
  • Coordinators
  • Documents
  • List of Programmes in English
  • ECTS / DS Labels

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS EKO 6107 SHALLOW AND DEEP LEARNING TECHNIQUES ELECTIVE 3 0 0 6

Offered By

Econometrics

Level of Course Unit

Third Cycle Programmes (Doctorate Degree)

Course Coordinator

ASSOCIATE PROFESSOR MURAT TANIK

Offered to

Econometrics

Course Objective

The main objectives of this course are to introduce basic definitions related to shallow and deep learning techniques, to provide information about current developments in learning concept, and to use the techniques given in the course for problems faced in real-life situations.

Learning Outcomes of the Course Unit

1   1. To be able to grasp the fundamental of artificial neural networks. 2   2. To be able to define the concept for shallow learning. 3   3. To be able to understand the idea behind deep learning. 4   4. To be able to find the solution to some problems encountered in real-life with deep learning. 5   5. To be able to employ software packages in constructing advanced neural networks architectures.

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description 1 Binary Genetic Algorithms 2 Selecting Parameters of Genetic Algorithm 3 Genetic Algorithm with Constant Parameters 4 Alternative Crossover and Mutation Techniques 5 Analysis of Genetic Algorithms with Matlab 6 1- To be able to understand the basic principle of artificial neural networks and shallow learning. 7 2- A neuron model and architecture of neural networks. 8 3- The backpropagation algorithm. 9 4- Variations on the backpropagation algorithm. 10 5- Generalization and practical issues. 11 6 - Some Case Studies 12 7- The differences between shallow and deep learning. 13 8- Mid-term 14 9- Mid-term 15 10- Long-short term memory neural networks. 16 11- Convolutional neural networks. 17 12- Autoencoders neural networks. 18 13- Practical issues in training deep learning models. 19 14- Applying the learned models in software packages.

Recomended or Required Reading

1. François Chollet. Deep Learning with Python. Manning Publications Co. 2017. 2. Aurelien Geron. Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow. Oreilly. 2019. 3. Hagan, M.T., Demuth, H.B. and Beale, M. Neural Network Design. 1996.

Planned Learning Activities and Teaching Methods

This course will be presented using class lectures, class discussions, overhead projections, and demonstrations.

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA 1 MTE MIDTERM EXAM 2 FCG FINAL COURSE GRADE 3 FCGR FINAL COURSE GRADE MTE * 0.40 + FCG* 0.60 4 RST RESIT 5 FCGR FINAL COURSE GRADE (RESIT) MTE * 0.40 + RST* 0.60

Further Notes About Assessment Methods

None

Assessment Criteria

To be announced.

Language of Instruction

Turkish

Course Policies and Rules

To be announced.

Contact Details for the Lecturer(s)

serkan.aras@deu.edu.tr

Office Hours

To be announced.

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours) Lectures 13 3 39 Preparations before/after weekly lectures 13 3 39 Preparation for midterm exam 1 30 30 Preparation for final exam 1 30 30 Midterm 1 3 3 Final 1 3 3 TOTAL WORKLOAD (hours) 144

Contribution of Learning Outcomes to Programme Outcomes

PO/LO PO.1 PO.2 PO.3 PO.4 PO.5 PO.6 PO.7 PO.8 PO.9 LO.1 3 3 3 2 3 3 2 3 3 LO.2 2 3 3 3 3 2 4 4 4 LO.3 5 5 2 3 3 3 3 3 3 LO.4 3 3 3 3 3 3 3 3 3 LO.5 2 2 3 3 2 2 2 2 2