COURSE UNIT TITLE

: ARTIFICIAL NEURAL NETWORKS AND APPLICATIONS IN PHYSICS

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
PHY 5192 ARTIFICIAL NEURAL NETWORKS AND APPLICATIONS IN PHYSICS ELECTIVE 3 0 0 7

Offered By

Graduate School of Natural and Applied Sciences

Level of Course Unit

Second Cycle Programmes (Master's Degree)

Course Coordinator

ASSOCIATE PROFESSOR ÜMIT AKINCI

Offered to

PHYSICS
PHYSICS

Course Objective

Today, ANN stands in a very important place both for understanding the emergence of intelligence and learning and for its potential applications in wide areas. On the other hand, problem-solving with ANN is a developing field. The aim of this course is to give the fundamentals of ANN to the students.

Upon successful completion of the course, students will comprehend the fundamentals of ANN and gain knowledge and ideas on how to solve various problems in physics with ANN.

Learning Outcomes of the Course Unit

1   To understand the basics of ANN and to recognize different architectures
2   To be able to recognize the learning strategies of ANN
3   To learn the perceptron network and working mechanism
4   To be able to recognize Boltzmann machines
5   To be able to make physical applications including differential equation solution with different ANN architectures
6   To be able to solve statistical physics problems with Boltzmann machines

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description
1 Introduction: Fundamentals and history of artificial neural networks (ANN)
2 Artificial neural network architectures and education process
3 Perceptron Network
4 ADALINE network
5 Multilayer Perceptron Network
6 Recurrent Hopfield networks
7 Midterm Exam I
8 Boltzmann machines
9 Solution of differential equations by ANN
10 Solution of Lagrange and Hamilton equations of motion by ANN
11 Solution of Schrodinger equation by ANN
12 Comparison of Boltzmann machines with MC simulation
13 Ising model solution with Boltzmann machines
14 Presentations of asignments

Recomended or Required Reading

Textbook(s):
Ivan Nunes da Silva, Danilo Hernane Spatti, Rogerio Andrade Flauzino, Luisa Helena, Bartocci Liboni,
Silas Franco dos Reis Alves, Artificial Neural Networks A Practical Course, Springer, 2017

Supplementary Book(s):
Pıerre Peretto, An Introductıon To The Modelıng Of Neural Networks, Cambridge university Press, 1994

Planned Learning Activities and Teaching Methods

Lecture, problem solving, homework

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 MTE MIDTERM EXAM
2 PRJ PROJECT
3 FIN FINAL EXAM
4 FCG FINAL COURSE GRADE MTE *0.25 + PRJ *0.45 +FIN *0.30
5 RST RESIT
6 FCGR FINAL COURSE GRADE (RESIT) MTE *0.25 +PRJ *0.45 +RST *0.30


Further Notes About Assessment Methods

None

Assessment Criteria

To be announced.

Language of Instruction

English

Course Policies and Rules

To be announced.

Contact Details for the Lecturer(s)

umit.akinci@deu.edu.tr/ Tınaztepe kampüsü öğretim üyeleri binası /223

Office Hours

Wednesday 13.00-15.00

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 10 3 30
Tutorials 2 3 6
Preparations before/after weekly lectures 12 4 48
Preparation for midterm exam 1 20 20
Preparation for final exam 1 20 20
Preparing assignments 5 10 50
Midterm 1 3 3
Final 1 3 3
TOTAL WORKLOAD (hours) 180

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10
LO.13544554532
LO.25554554432
LO.35544554432
LO.44544554432
LO.55544454432
LO.64544554532