NEURAL NETWORKS for SIGNAL PROCESSING

AIM

The objective of the course is to evaluate the signal processing and pattern recognition techniques based on utilization of computational neurons.

CONTENT

This course contains; The Nervous System: Microscopic View,The Nervous System: Macroscopic View,Machine Learning and Pattern Recognition,Perceptron,Multilayer Perceptron,Supervised Learning,Backpropogation Algorithm,Neural Networks for Regression,Neural Networks for Pattern Recognition,Hodgkin-Huxley And Izhikevich Model,Mathematical Models of Synaptic Interactions,Neuromodulation – Reinforcement Learning,Spiking Neural Networks,Spiking Neural Network Simulation.

1. 1

   Designs neural networks for signal processing and pattern recognition problems.

   Taught by: Discussion Method, Self Study Method, Question - Answer Technique, Experimental Technique, Brainstorming Technique, Project Based Learning Model, Simulation Technique, Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

2. 2

   Evaluates fundamental neuron and synaptics interaction models.

   Taught by: Discussion Method, Self Study Method, Question - Answer Technique, Experimental Technique, Brainstorming Technique, Project Based Learning Model, Simulation Technique, Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

3. 3

   Explains key concepts in neural coding.

   Taught by: Discussion Method, Self Study Method, Question - Answer Technique, Experimental Technique, Brainstorming Technique, Project Based Learning Model, Simulation Technique, Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

4. 4

   Evaluates the use of model neurons in computational models of the components of the nervous system.

   Taught by: Discussion Method, Self Study Method, Question - Answer Technique, Experimental Technique, Brainstorming Technique, Project Based Learning Model, Simulation Technique, Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

5. 5

   Designs neural networks for regression problems.

   Taught by: Discussion Method, Problem Solving Method, Case Study Method, Self Study Method, Question - Answer Technique, Brainstorming Technique, Project Based Learning Model, Simulation Technique, Cooperative Learning, Experiential Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

6. 6

   Provides solutions for classification problems using neural networks.

   Taught by: Discussion Method, Problem Solving Method, Self Study Method, Question - Answer Technique, Brainstorming Technique, Project Based Learning Model, Simulation Technique, Cooperative Learning, Flipped Classroom Learning, Lecture Method · Assessed by: Traditional Written Exam, Homework, Project Task

WEEKLY PLAN

1. WEEK 1

   The Nervous System: Microscopic View

2. WEEK 2

   The Nervous System: Macroscopic View

3. WEEK 3

   Machine Learning and Pattern Recognition

4. WEEK 4

   Perceptron

5. WEEK 5

   Multilayer Perceptron

6. WEEK 6

   Supervised Learning

7. WEEK 7

   Backpropogation Algorithm

8. WEEK 8

   Neural Networks for Regression

9. WEEK 9

   Neural Networks for Pattern Recognition

10. WEEK 10

    Hodgkin-Huxley And Izhikevich Model

11. WEEK 11

    Mathematical Models of Synaptic Interactions

12. WEEK 12

    Neuromodulation – Reinforcement Learning

13. WEEK 13

    Spiking Neural Networks

14. WEEK 14

    Spiking Neural Network Simulation

ASSESSMENT

• Rate of Midterm Exam to Success50%
• Rate of Final Exam to Success50%

WORKLOAD

READING

• Alpaydin, E., (2010) Introduction to machine learning, MIT Press,Cambridge. Kandel, E. R., Schwartz, J. H., Jessell, T. M., Siegelbaum, S. A., Hudspeth, A. J. , (2012) Principles of neural science, McGraw-Hill, New York. Lytton, W. W., (2002) From computer to brain : foundations of computational neuroscience, Springer, New York. Dayan, P., Abbott, L. F., (2001) Theoretical neuroscience: Computational and mathematical modeling of neural systems, MIT Press, Cambridge. Izhikevich, E.M., (2007) Dynamical systems in neuroscience: The geometry of excitability and bursting, MIT Press, Cambridge.

TEACHING STAFF

• Assist.Prof. Mehmet KOCATÜRKCOORDINATOR
• Assist.Prof. Mehmet KOCATÜRK