Akademik Dersler - Öğrenme Çıktıları ile Program Yeterlilik İlişkisi

Last Updated: 23/06/2026

0 : Does not support 1 : Low-level support 2 : Mid-level support 3 : Top level support

Learning Outcomes		Program Qualifications
		PY1	PY2	PY3	PY4	PY5	PY6	PY7	PY8	PY9	PY10	PY11	PY12	PY13	PY14	PY15
LO-1	Upon successful completion of this course, students will gain the competence to grasp the basic concepts of deep learning and the development process of artificial neural networks to design multi-layer architectures with feedforward networks and activation functions, optimize model training using the backpropagation algorithm, loss functions, and gradient descent methods, apply regularization techniques such as early stopping and data augmentation to prevent overfitting, model and train convolutional (CNN) and recurrent (RNN/LSTM) neural networks for image processing and time series analysis tasks, and design distributed model training processes using hardware accelerators in big data environments with modern deep learning libraries.	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-