defter*
defter / katalog / EEE 543
EEE 543

Neural Networks

A graduate-level deep dive into how neural networks actually learn — starting from a single neuron's math and building up through backprop, recurrence, and attention to the architectures behind modern vision, language, and generative models. The bulk of the work happens in four projects where you implement and train these systems yourself, backed by quizzes that check whether you really understand the optimization and generalization theory underneath. It assumes you are comfortable with linear algebra, probability, and optimization, and serves as the foundation most EEE students need before tackling research in computer vision, NLP, or any ML-adjacent thesis work.

Credit3ECTS5FacultyFaculty of EngineeringBölümElectrical and Electronics Engineering

Önerilen kaynaklar 2 kitap

📕
Zorunlu
Deep Learning
Ian Goodfellow and Yoshua Bengio and Aaron Courville
2016 · The MIT Press
📖
Önerilen
Neural Networks : A Comprehensive Foundation
S. Haykin
1999/2nd · Macmillan

Haftalık müfredat 14 hafta

Hafta 1
Primer on Linear Algebra, Probability and Optimization for Machine Learning / Introduction to Neural Networks (NNs)
Hafta 2
Neurons: Biophysical and Mathematical Models
Hafta 3
Neural Network Structures: Perceptrons
Hafta 4
Learning Algorithms , Supervised, Unsupervised, Reinforcement Learning
Hafta 5
Training Single Layer NNs
Hafta 6
Training Multilayer NNs: Back Propagation, Empirical Risk Minimization
Hafta 7
Optimization Methods and Generalization
Hafta 8
Recurrent Neural Networks (RNNs): BP Through Time, LSTM
Hafta 9
Restricted Boltzmann Machines (RBMs): Contrastive Divergence
Hafta 10
Autoencoders: Denoising, Contractive, Stacked NNs
Hafta 11
Deep Learning: Deep Autoencoders, Deep Belief Networks
Hafta 12
Vision Models: Convolutional NNs for Computer Vision
Hafta 13
Language Models: RNNs for Natural Language Processing
Hafta 14
Generative Modeling: Adversarial Models, Variational Models, Diffusion Probabilistic Models

🤖 GenAI politikası

Generative AI tools (e.g., large language models, coding assistants, and image-generation tools) may be used for take-home assessments (i.e., tutorial/homework and project assignments) to assist with coding, and improving writing. Any use of generative AI must be clearly disclosed, including the name/version of the tool and a brief description of how it was used. Upon request, students should be ready to provide prompts, outputs, and execution logs pertaining to their genAI use for all assignmen

Ders notları — henüz yok

EEE 543 için defter ekibi henüz not yazmadı.

İlk dosyayı sen atarsan — not, slayt, geçmiş sınav, çözüm, cheat-sheet, ne varsa — defter ekibi öğrenci paylaşımlarından bu dersin notlarını yazar. Drive linki / PDF / ZIP, hepsi olur.

← katalog

Geçmiş GPA dağılımı 22 dönem · ort. 3.46

DönemCourse CPA
2025-2026 Fall 3.68 1 sec · 17 öğr
2024-2025 Fall 3.59 1 sec · 18 öğr
2024-2025 Spring 3.34 1 sec · 20 öğr
2023-2024 Fall 3.37 1 sec · 23 öğr
2022-2023 Fall 3.68 1 sec · 18 öğr
2022-2023 Spring 3.58 1 sec · 12 öğr
2021-2022 Fall 3.41 1 sec · 9 öğr
2021-2022 Spring 3.60 1 sec · 14 öğr
2020-2021 Fall 3.40 1 sec · 14 öğr
2019-2020 Fall 3.38 1 sec · 15 öğr

Aggregate course GPA — Bilkent STARS'tan public data. Hoca-bazlı per-section detayı için STARS evaluation report →. Öğrenci anket cevapları KVKK kapsamında defter'de tutulmaz.

⚠️ FZ engelleyen şartlar

All in-class and take-home assignments should be completed and submitted. Grades, except the final exam, should justify a letter grade of D or better. (Note that meeting this criterion does not guarantee that you will eventually pass the course. Your letter grade still depends on your overall performance including the final.)

Hocalar 1 bu dönem · 3 geçmiş

Bu dönem (2025-2026 Spring) · 1 section
Tolga Çukur
Geçmişte ders veren (3 kişi)
Ömer Morgül, Erdem Koyuncu, Cem Tekin