At the end of this course, the students; 1) Understand what artificial neural network (ANN) means. 2) Comprehend the importance of ANNs for psychology and neuroscience. 3) Can discuss about how ANNs work. 4) Can discuss about ANN types. 5) Gain the opportunity to simulate learning with a simple neural network simulator.
MODE OF DELIVERY
Face to face
PRE-REQUISITES OF THE COURSE
No
RECOMMENDED OPTIONAL PROGRAMME COMPONENT
None
COURSE DEFINITION
This course aims to teach about the artificial neural network and their usage in modelling of human behavior and cognitive processes. The course will involve the structure of artificial neural networks, connection geometry, network parameters, network types, threshold functions, learning paradigms and network learning algorithms, memory properties, generalization and computational power. Also, the course will cover topics such as perceptron models, connectionism and connectionist models and parallel distributed processing. By giving artificial neural networks built for visual perception, learning, language acquisition, speech perception and memory research, students will gain information about the place of artificial neural network in psychological research.
COURSE CONTENTS
WEEK
TOPICS
1st Week
Introduction
2nd Week
Properties of Neurons
3rd Week
Artificial Neurons and Neural Networks
4th Week
Lateral Inhibition and Sensory Processing
5th Week
ANN Types and Their History
6th Week
Artificial Network Algorithms
7th Week
Learning Algorithms
8th Week
T-Learn Neural Network Simulation Program
9th Week
Creating a Simple Neural Network with T-Learn
10th Week
ANN Discussions
11th Week
Representation of Knowledge
12th Week
ANNs and Neuroscience
13th Week
Hybrid Models
14th Week
General Evaluation
RECOMENDED OR REQUIRED READING
Anderson, J.A., (1995). An Introduction to Neural Networks. MIT Press.
Bar-Yam, Y. (1997). Dynamics of complex systems. Addison-Wesley.
Rumelhart, D. & J. McClelland (1986). Parallel distributed processing. MIT Press, Cambridge, Mass * The basic materials to be used in this course are updated every year.
PLANNED LEARNING ACTIVITIES AND TEACHING METHODS
Lecture,Discussion
ASSESSMENT METHODS AND CRITERIA
Quantity
Percentage(%)
Project
1
60
Total(%)
60
Contribution of In-term Studies to Overall Grade(%)
60
Contribution of Final Examination to Overall Grade(%)
40
Total(%)
100
ECTS WORKLOAD
Activities
Number
Hours
Workload
Midterm exam
Preparation for Quiz
Individual or group work
14
5
70
Preparation for Final exam
1
24
24
Course hours
14
3
42
Preparation for Midterm exam
Laboratory (including preparation)
Final exam
1
3
3
Homework
1
160
160
Total Workload
299
Total Workload / 30
9,96
ECTS Credits of the Course
10
LANGUAGE OF INSTRUCTION
Turkish
WORK PLACEMENT(S)
No
KEY LEARNING OUTCOMES (KLO) / MATRIX OF LEARNING OUTCOMES (LO)