Akademik Dersler - Tanıtım

Last Updated: 23/06/2026

Code - Course Title	Course Type	Laboratory + Practice	ECTS
BVA223 - Deep Learning Fundamentals	III. SEMESTER	2 +1	3.0

Language of Instruction	Türkçe
Course Type	Area Elective Courses
Course Instructor(s)	ÖĞR. GÖR. AHMET MÜCAHİD ARVASİ
Mode of Delivery	Face to face
Place of Delivery
Used Educational Platforms
Prerequisites	There are no prerequisites or corequisites for this course.
Courses Recomended
Recommended Resources
Work Placement
Aims of the Course

Weeks	Learning Outcomes	Topics	Teaching Methods
Week - 1		Introduction to Deep Learning: Basic Concepts and Historical Development of Artificial Neural Networks
Week - 2		Feedforward Neural Networks (FNN): Perceptron Architecture and Working Principle
Week - 3		Multi-Layer Structures (MLP) and Activation Functions (Sigmoid, ReLU, Tanh)
Week - 4		Model Training 1: Loss Functions and Gradient Descent Methods
Week - 5		Model Training 2: Backpropagation Algorithm and Its Mathematical Foundations
Week - 6		Optimization Techniques (Adam, RMSprop) and Learning Rate Management
Week - 7		Overfitting and Regularization: Early Stopping and Dropout Methods
Week - 8		Midterm Exam
Week - 9		Data Augmentation and Model Validation Techniques
Week - 10		Introduction to Convolutional Neural Networks (CNN): Image Processing Fundamentals and Filters
Week - 11		CNN Architectures: Pooling Layers and Feature Extraction
Week - 12		Recurrent Neural Networks (RNN): Time Series Analysis and Sequential Data Processing
Week - 13		Advanced Recurrent Structures: Long Short-Term Memory (LSTM) and GRU Architectures
Week - 14		Deep Learning with Big Data: Distributed Model Training, Hardware Accelerator (GPU/TPU) Usage, and Project Presentations

No content has been provided.

No content has been provided.

No content has been provided.

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