At the end of this course, the students; 1) Understand what an artificial neural network (ANN) is. 2) Understand why ANN's are crucial for psychology and neuroscience. 3) Gain knowledge about how ANN's work. 4) Gain knowledge about different types of ANN's. 5) Find opportunity to simulate a learning system with an easy neural net simulator.
MODE OF DELIVERY
Face to face
PRE-REQUISITES OF THE COURSE
No
RECOMMENDED OPTIONAL PROGRAMME COMPONENT
None
COURSE DEFINITION
This course introduces students to artificial neural networks and the use of artificial neural networks in the modeling of human behavior and cognition. Topics covered in the course include: the structure and components of artificial neural networks, connection geometry, network parameters, network types, threshold functions, learning paradigms and algorithms, memory properties, generalization and computational power of artificial neural networks. The course also examines the perceptron model, connectionism and connectionist models, and parallel distributed processing. Drawing on sample network models of visual perception, learning, speech perception, language acquisition, and learning, the course aims to inform students of the use of artificial neural networks in psychological research.
COURSE CONTENTS
WEEK
TOPICS
1st Week
Introduction
2nd Week
Neurons
3rd Week
Artificial Neurons and Artificial Neural Networks
4th Week
Lateral Inhibition and Sensory Processing
5th Week
Types and History of ANN
6th Week
Artificial Network Algorithms
7th Week
Learning Algorithms
8th Week
T-learn Neural Network Simulation Program
9th Week
Constructing a simple ANN with T-learn
10th Week
Criticisms of ANN
11th Week
Representation of Information
12th Week
ANN's and Neuroscience
13th Week
Hybrid Models
14th Week
Integration and Review Session
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.
PLANNED LEARNING ACTIVITIES AND TEACHING METHODS
Lecture,Discussion
ASSESSMENT METHODS AND CRITERIA
Quantity
Percentage(%)
Mid-term
1
30
Project
1
40
Total(%)
70
Contribution of In-term Studies to Overall Grade(%)
70
Contribution of Final Examination to Overall Grade(%)
30
Total(%)
100
ECTS WORKLOAD
Activities
Number
Hours
Workload
Midterm exam
1
3
3
Preparation for Quiz
Individual or group work
14
8
112
Preparation for Final exam
1
20
20
Course hours
14
3
42
Preparation for Midterm exam
1
15
15
Laboratory (including preparation)
Final exam
1
3
3
Homework
Project
1
10
10
Total Workload
205
Total Workload / 30
6,83
ECTS Credits of the Course
7
LANGUAGE OF INSTRUCTION
Turkish
WORK PLACEMENT(S)
No
KEY LEARNING OUTCOMES (KLO) / MATRIX OF LEARNING OUTCOMES (LO)