defter / katalog / ME 505

ME 505

Machine Learning for Mechanical Engineering

ME 505 treats machine learning as a working tool for mechanical engineering problems rather than as pure CS theory, so the emphasis is on turning physical data, microscopy images, material properties, atomistic simulations, into models that actually predict something useful. You'll spend the semester writing Python, curating real datasets, and building up from linear regression through neural networks to ML potentials for molecular dynamics and reinforcement-learning-driven self-driving labs, capped by a project you present to the class. It's a graduate-level bridge course for ME students who already have the mechanics background but need the data-driven half, and it sets you up for materials informatics research and any modern simulation work where ML surrogates have replaced hand-tuned models.

Kredi3ECTS5FakülteFaculty of EngineeringBölümMechanical EngineeringKoordinatörOrçun Koray Çelebi

→ STARS müfredatı (resmi syllabus)

Haftalık müfredat 14 hafta

Hafta 114–20 Eyl

Machine learning ve Python ile istatistik

Course outline, introduction to machine learning, data driven approach for mechanical engineering, algebra and statistics with Python

machine learningdata driven approachalgebraPython

Hafta 221–27 Eyl

Makine öğrenmesi yöntemlerine genel bakış

Overview of supervised, unsupervised and reinforcement learning methods

supervised learningunsupervised learningreinforcement learning

Hafta 328 Eyl – 4 Eki

Deployment, rastgele sayılar ve veri yönetimi

Deployment, random numbers, data management

deploymentrandom numbersdata management

Hafta 45–11 Eki

Makine Mühendisliğinde Veri Türleri ve Curation

Data types in mechanical engineering, online data repositories, data analysis, cleanup, preparation, curation

data typesonline data repositoriesdata cleanupcuration

Hafta 512–18 Eki

Linear regression, validation ve model seçimi

Linear regression, validation, evaluation, feature engineering, descriptor selection, tuning and model selection

linear regressionfeature engineeringdescriptor selectionmodel selection

Hafta 619–25 Eki

Regression modelleri

Regression models

regression model

Hafta 726 Eki – 1 Kas

Classification modelleri

Classification models

classification models

Hafta 82–8 Kas

Materials database kullanımı

Usage of materials databases

materials database

Hafta 99–15 Kas

Neural networks ve deep learning

Neural networks, deep learning

neural networksdeep learning

Hafta 1016–22 Kas

Atomistic machine learning

Hafta 1123–29 Kas

Atomistic descriptor'lar ve materials ontology

Atomistic descriptors, materials ontologies

atomistic descriptorsmaterials ontologies

Hafta 1230 Kas – 6 Ara

Molecular dynamics için machine learning potentials

Machine learning potentials for molecular dynamics

machine learning potentialsmolecular dynamics

Hafta 137–13 Ara

Reinforcement learning ve self-driving labs

Reinforcement learning, self-driving labs

reinforcement learningself-driving lab

Hafta 1414–20 Ara

Proje sunumları

Project presentations

proje sunumu

Bu dersi alınca · 5 öğrenme çıktısı

Curate and manage data in databases, visualize data, transform it into descriptors compatible with machine learning modelsMidterm Project Final Homework
Utilize supervised, unsupervised, reinforcement learning methods on various data sets in mechanical engineeringMidterm Project Final Homework
Apply regression, classification, and deep learning models to solve mechanical engineering problemsMidterm Project Final Homework
Communicate their reasoning effectively to their peersProject Homework
Collaborate professionally and scientifically with their peersProject

Bilkent'in resmî syllabus'ünden. Sağdaki etiket o çıktının hangi değerlendirmeyle ölçüldüğünü söylüyor.

🤖 GenAI politikası

Students are advised to consult their instructor regarding the use of Generative AI tools and their appropriateness. Responsible use of GenAI is encouraged in accordance with Bilkent University's GenAI Guidelines (https://w3.bilkent.edu.tr/bilkent/generative-artificial-intelligence-genai-guideline).

Ders notları · henüz yok

ME 505 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

Bu dönem · 2026-2027 Güz · 1 şube · 10 kontenjan

haftada 3 saat ders

Haftalık ızgarada 4 saat görünüyor, kayıt sistemi dersi 3 saat yazıyor. Aradaki 1 saat yedek saat: Bilkent programlarında derse genelde bir fazla saat ayrılır ve çoğu zaman kullanılmaz. Hangisinin düşeceği dönem başlayınca belli olur.

Orçun Koray Çelebi

Çar10:30–12:20Cum15:30–17:20

kişilik

programıma ekle → CGPA'ya ekle kayıt tarihleri

⚠️ FZ engelleyen şartlar

No FZ grade is given in this course

Hocalar 1 bu dönem · 0 geçmiş

Bu dönem (2026-2027 Fall) · 1 section

Orçun Koray Çelebi