NEURAL NETWORKS

AIM

The objective of the course is to evaluate the information processing techniques and control algorithms based on utilization of computational neurons.

CONTENT

This course contains; The Nervous System: Microscopic View,The Nervous System: Macroscopic View,Perceptron,Multilayer Perceptron,Supervised Learning,Hodgkin-Huxley Model,Izhikevich Model,Synaptic Interaction Models,Neuromodulation – Reinforcement Learning,Spike Timing - Oscillations,Spiking Neural Network Simulation,Real-time Spiking Neural Network Simulation,Neuromorphic Processors,Large-Scale Neuronal Network Modeling.

1. 1

   Describes and evaluates fundamental neuron and synaptics interaction models.

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

2. 2

   Explains key concepts in neuronal coding.

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

3. 3

   Explains dynamics of biological neuronal circuits using mathematical modeling techniques.

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

4. 4

   Identifies hardware and software tools for neuronal network simulations.

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

5. 5

   Creates artificial neural networks to resolve engineering problems.

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

WEEKLY PLAN

1. WEEK 1

   The Nervous System: Microscopic View

   Preparation: Week 1 lecture notes.

2. WEEK 2

   The Nervous System: Macroscopic View

   Preparation: Week 1 lecture notes (continued).

3. WEEK 3

   Perceptron

   Preparation: Week 3 lecture notes.

4. WEEK 4

   Multilayer Perceptron

   Preparation: Week 4 lecture notes.

5. WEEK 5

   Supervised Learning

   Preparation: Week 5 lecture notes.

6. WEEK 6

   Hodgkin-Huxley Model

   Preparation: Week 6 lecture notes.

7. WEEK 7

   Izhikevich Model

   Preparation: Week 7 lecture notes.

8. WEEK 8

   Synaptic Interaction Models

   Preparation: Week 8 lecture notes.

9. WEEK 9

   Neuromodulation – Reinforcement Learning

   Preparation: Week 9 lecture notes.

10. WEEK 10

    Spike Timing - Oscillations

    Preparation: Week 10 lecture notes.

11. WEEK 11

    Spiking Neural Network Simulation

    Preparation: Week 11 lecture notes.

12. WEEK 12

    Real-time Spiking Neural Network Simulation

    Preparation: Week 12 lecture notes.

13. WEEK 13

    Neuromorphic Processors

    Preparation: Week 13 lecture notes.

14. WEEK 14

    Large-Scale Neuronal Network Modeling

    Preparation: Week 14 lecture notes.

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. Lytton, W. W., (2002) From computer to brain : foundations of computational neuroscience, Springer, New York. Kandel, E. R., Schwartz, J. H., Jessell, T. M., Siegelbaum, S. A., Hudspeth, A. J. , (2012) Principles of neural science, McGraw-Hill, 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