defter*
defter / katalog / EEE 443
EEE 443

Neural Networks

Biological neural networks. Artificial neural networks. Basic neuron. Modeling the single neuron. Feed-forward architectures. Recurrent neural networks. Restricted boltzmann machines. Learning algorithms. Back propagation. Contrastive divergence. Optimization and generalization for neural networks. Autoencoders. Deep belief networks. Convolutional neural networks. Long short-term memory networks. Self-attention and transformers. Adversarial networks.

Credit3
ECTS5
BölümElectrical and Electronics Engineering
FacultyFaculty of Engineering
PrereqEEE 321 or EEE 391

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

→ STARS müfredatı / syllabus

Materyal — 0 dosya

Bu derste henüz materyal yok.

İlk dosyayı sen ekleyebilirsin — notlar, geçmiş finaller, çözümler, cheat-sheet, ne varsa. Drive linki / PDF / ZIP / fotoğraf, hepsi olur.

Şu an: mail at, ben düzenleyip yayına alayım. Form/upload UX yakında geliyor (Kimya tasarlıyor).

↑ konuya EEE 443 yaz

Geçmiş GPA dağılımı 22 dönem · ort. 2.79

DönemCourse CPA
2025-2026 Fall 3.25 1 sec · 67 öğr
2024-2025 Fall 3.34 1 sec · 65 öğr
2024-2025 Spring 3.03 1 sec · 64 öğr
2023-2024 Fall 3.37 1 sec · 46 öğr
2022-2023 Fall 2.67 1 sec · 59 öğr
2022-2023 Spring 3.06 1 sec · 30 öğr
2021-2022 Fall 3.24 1 sec · 53 öğr
2021-2022 Spring 2.69 1 sec · 38 öğr
2020-2021 Fall 2.87 1 sec · 50 öğr
2019-2020 Fall 2.86 1 sec · 71 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.

Müfredat detayı STARS syllabus

📚 Önerilen kaynaklar

  • Zorunlu Deep Learning Ian Goodfellow and Yoshua Bengio and Aaron Courville · 2016 · The MIT Press
  • Önerilen Neural Networks and Learning Machines Simon S. Haykin · 2009 · Upper Saddle River: Pearson Education
  • Önerilen Introduction to Artificial Neural Systems J. M. Zurada · 1992. · West Pub. Co

⚖️ Değerlendirme

  • 25% — Quiz: Quiz Average (×1)
  • 15% — Homework: Tutorial Average (×1)
  • 10% — Project: Project Assignment 1 (×1)
  • 10% — Project: Project Assignment 2 (×1)
  • 10% — Project: Project Assignment 3 (×1)
  • 30% — Project: Final Project (×1)

⚠️ 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.)

🤖 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

📅 Haftalık müfredat

Primer on Linear Algebra, Probability and Optimization for Machine Learning / Introduction to Neural Networks (NNs) Neurons: Biophysical and Mathematical Models Neural Network Structures: Perceptrons Learning Algorithms: Supervised, Unsupervised, Reinforcement Learning Training Single Layer NNs Training Multilayer NNs: Back Propagation, Empirical Risk Minimization Optimization Methods and Generalization Recurrent Neural Networks (RNNs): BP Through Time, LSTM Restricted Boltzmann Machines (RBMs): Contrastive Divergence Autoencoders: Denoising, Contractive, Stacked NNs Deep Learning: Deep Autoencoders, Deep Belief Networks Vision Models: Convolutional and Transformer Networks for Computer Vision Language Models: RNNs and Transformers for Natural Language Processing Generative Modeling: Adversarial Models, Variational Models, Diffusion Probabilistic Models ECTS - Workload Table: Activities Number Hours Workload Course hours 14 3 42 Project (including preparation and presentation if applicable) 4 25 100 Quiz 3 1 3 Preparation for Quiz 3 4 12 Total Workload: 157 Total Workload / 30: 157 / 30 5.23 ECTS Credits of the Course: 5 Type of Course: Lecture - Project - Independent Study Course Material: Written - Multimedia Teaching Methods: Lecture