This course will introduce the fundamental ideas and techniques underlying the design of intelligent systems. Topics to be covered: Search methods, optimality and heuristics for problem solving. Probability theory, decision-making in fully informed, partially observable and adversarial settings. Introductory level: Learning via interaction with the environment (reinforcement learning). Learning from data (machine/deep learning). Graphical models and causality. Application domains of the (state-of-the-art) methods.
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 | |
|---|---|---|
| 2024-2025 Fall | 2.98 | 1 sec · 66 öğr |
| 2023-2024 Fall | 2.68 | 1 sec · 56 öğr |
| 2022-2023 Spring | 2.51 | 1 sec · 65 öğr |
| 2021-2022 Spring | 2.58 | 1 sec · 66 öğr |
| 2020-2021 Fall | 2.91 | 2 sec · 126 öğr |
| 2020-2021 Spring | 2.61 | 2 sec · 87 öğr |
| 2019-2020 Fall | 2.99 | 2 sec · 140 öğr |
| 2019-2020 Spring | 2.85 | 2 sec · 136 öğr |
| 2018-2019 Fall | 2.75 | 1 sec · 80 öğr |
| 2018-2019 Spring | 2.88 | 1 sec · 84 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.
At least 30% average on homeworks, 30% on quizzes, and 30% on the midterm required
We follow the Generative AI policy guideline of Bilkent University which can be found here: https://w3.bilkent.edu.tr/bilkent/generative-artificial-intelligence-genai-guideline/
Introduction to (Artificial) Intelligence, and Search Problems Problem Solving by (Uninformed) Search Problem Solving by Search, Optimality, Heuristics, and Adversarial Search Probabilistic Reasoning (Bayes Nets: Representation, (Conditional) Independence) Probabilistic Reasoning (Bayes Nets: Inference, Sampling) Probabilistic Reasoning (Advanced Topics: HMMs, Particle/Kalman Filters, etc.) Sequential Decision Making: Markov Decision Processes (MDPs), Reinforcement Learning (RL) Sequential Decision Making: MDPs, RL Function Approximation: Why and How? Function Approximation: Why and How? Deep Reinforcement Learning (DRL) DRL Evolutionary Algorithms, Genetic Algorithms, Evolutionary Strategies Learning/AI for Robotics ECTS - Workload Table: Activities Number Hours Workload Preparation for Final exam 1 12 12 Midterm exam 1 2 2 Course hours 14 3 42 Final exam 1 2 2 Report (including preparation and presentation if applicable) 1 10 10 Project (including preparation and presentation if applicable) 1 40 40 Preparation for Midterm exam 1 12 12 Homework 6 5 30 Total Workload: 150 Total Workload / 30: 150 / 30 5 ECTS Credits of the Course: 5 Type of Course: Lecture - Project Course Material: Slides - LMS (Moodle, etc) Teaching Methods: Lecturing - Assignment - Independent study