Akademik Dersler - Tanıtım


Code - Course Title	YZM3007 - Artificial Neural Networks
Course Type	Required Courses
Language of Instruction	İngilizce
Laboratory + Practice	3+0
ECTS	4.0
Course Instructor(s)	DOKTOR ÖĞRETİM ÜYESİ NİHAL İNCE
Mode of Delivery	This course is offered exclusively in an in-person format.
Prerequisites	There are no prerequisites or co-requisites for this course.
Courses Recomended	There are no other recommended courses related to this one.
Required or Recommended Resources	Aggarwal, C. C. (2018). Neural networks and deep learning: A textbook. Springer. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. Murphy, K. P. (2022). Probabilistic machine learning: An introduction. MIT Press.
Recommended Reading List	Aggarwal, C. C. (2018). Neural networks and deep learning: A textbook. Springer. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. Murphy, K. P. (2022). Probabilistic machine learning: An introduction. MIT Press.
Assessment methods and criteria	2midterm exams, 1 final exam
Work Placement	This is not suitable for this class.
Sustainability Development Goals

Weeks	Topics
Week - 1	Introduction: From Biological to Artificial Neurons. The Perceptron. The XOR Problem and Non-Linearity.
Week - 2	The Multi-Layer Perceptron (MLP). Activation Functions.
Week - 3	Optimization: The Gradient Descent Algorithm.
Week - 4	The Backpropagation Algorithm. The Chain Rule and Gradient Calculation.
Week - 5	Implementation of Backpropagation Algorithm
Week - 6	The TensorFlow and Keras APIs. Building an MLP with Keras.
Week - 7	The Training Process: Stochastic Gradient Descent (SGD), Mini-Batch, Epochs. Optimizers (Adam, RMSprop).
Week - 8	Overfitting in Deep Networks: Regularization (L2) and Dropout.
Week - 9	Convolutional Neural Networks (CNNs) I: Introduction. The Convolutional Layer (Filters, Stride).
Week - 10	The Pooling Layer. Coding a simple CNN with Keras.
Week - 11	CNN Architectures: LeNet, AlexNet. The Concept of Transfer Learning.
Week - 12	Recurrent Neural Networks (RNNs): Sequential Data. The Simple RNN cell and its problems.
Week - 13	Vanishing/Exploding Gradients. Long-Short Term Memory and Gated Recurrent Unit Cells.
Week - 14	Conceptual Introduction to Autoencoders or Generative Adversarial Networks (GANs).

Assessment Method and Passing Requirements
	Quamtity	Percentage (%)
Toplam (%)		0