Introduction to the goals and tools of machine learning and data analytics. Overview of machine learning on diverse data acquired by: sensor networks, physiological devices, etc. Fundamental learning models. Applications: decision support, computer vision, recommender systems. Performance analysis by using probabilistic approach. Bayesian and frequentist machine learning. Classification and regression. Linear regression, Ridge regression, Lasso. Parameter estimation and Bayesian regression. Generalized linear models. Neural Networks. Learning from unlabeled data: probabilistic clustering, blind signal separation and feature extraction. Graphical models. Techniques for handling missing and corrupted data. Deep learning, transfer learning, online learning.
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).
| Dönem | Course CPA | |
|---|---|---|
| 2025-2026 Fall | 2.78 | 1 sec · 70 öğr |
| 2024-2025 Fall | 2.69 | 1 sec · 66 öğr |
| 2023-2024 Fall | 2.33 | 1 sec · 64 öğr |
| 2023-2024 Spring | 2.43 | 1 sec · 70 öğr |
| 2022-2023 Fall | 2.29 | 1 sec · 47 öğr |
| 2022-2023 Spring | 2.50 | 2 sec · 103 öğr |
| 2021-2022 Fall | 2.54 | 1 sec · 30 öğr |
| 2021-2022 Spring | 2.48 | 2 sec · 86 öğr |
| 2020-2021 Fall | 2.17 | 1 sec · 43 öğr |
| 2020-2021 Spring | 2.66 | 2 sec · 92 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.
All project reports should be completed and submitted on time. No disciplinary penalty related with the course. The total points collected from the midterm and quizzes should be at least 20% of the total contribution of the midterm and quizzes.
Probability review for machine learning and data science (random variables, random vectors, Bayes rule, independence, law of large numbers, concentration inequalities Bayesian and frequentist machine learning (credible intervals, confidence intervals) and their use in data science Linear regression, ordinary least squares Ridge regression, lasso, Bayesian linear regression Generalized linear models Perceptron, neural networks and backpropagation Blind signal separation Probabilistic clustering, mixture of Gaussians and expectation maximization Feature extraction and feature selection Inference and learning in graphical models Naive Bayes, Restricted Boltzmann Machines, Contrastive Divergence Deep learning Reinforcement learning Online learning ECTS - Workload Table: Activities Number Hours Workload Course hours 14 3 42 Project (including preparation and presentation if applicable) 1 40 40 Midterm exam 1 2 2 Homework 4 5 20 Final exam 1 3 3 Preparation for Midterm exam 1 20 20 Preparation for Final exam 1 20 20 Total Workload: 147 Total Workload / 30: 147 / 30 4.9 ECTS Credits of the Course: 5