Akademik Dersler - Tanıtım

Last Updated: 03/10/2025

Code - Course Title	Compulsory/Elective	Laboratory + Practice	ECTS
BVA213 - Artificial Neural Networks	III. SEMESTER	2 +0	2.0

Language of Instruction	Türkçe
Course Type	Area Elective Courses
Course Instructor(s)	PROF. DR. ALPER TOLGA KUMTEPE
Mode of Delivery	Face to face
Place of Delivery
Used Educational Platforms
Prerequisites	Basic Mathematical Knowledge
Courses Recomended	Basic Mathematical Knowledge
Recommended Resources	Faculty Recommendation
Work Placement	N/A
Aims of the Course

Weeks	Learning Outcomes	Topics	Teaching Methods
Week - 1		Course introduction, history of artificial neural networks, and their relation to biological neural systems.
Week - 2		Artificial neuron model, input-output relationships, and basic activation functions (sigmoid, tanh, ReLU).
Week - 3		Structure of single-layer and multi-layer perceptrons (MLP) and introduction to feedforward networks.
Week - 4		Forward propagation and backpropagation algorithms, and loss functions.
Week - 5		Gradient descent and optimization techniques; learning rate and epoch concepts.
Week - 6		Overfitting and regularization techniques, dropout, L1/L2 regularization.
Week - 7		Supervised learning applications: classification and regression problems.
Week - 8		Unsupervised learning and Kohonen networks (self-organizing maps).
Week - 9		Introduction to recurrent neural networks (RNN), applications in time series and sequences.
Week - 10		Hopfield networks and the basic principles of energy-based models.
Week - 11		Introduction to Boltzmann machines and restricted Boltzmann machines (RBM).
Week - 12		Fundamentals of convolutional neural networks (CNN) and applications in image processing.
Week - 13		Comparison of network architectures, advantages and disadvantages; real-world data applications.
Week - 14		Presentation of term projects, overall evaluation, and brief look at advanced topics.

No content has been provided.

No content has been provided.

No content has been provided.

Assessment Method and Passing Requirements
	Quamtity	Percentage (%)
Toplam (%)