For up-to-date information check out the Artificial Intelligence VIMIAC10 Teams group 2024 Fall:

Artificial Intelligence - BMEVIMIAC10-EN | Általános | Microsoft Teams

Lectures from previous semesters

Lecture 1:

Introduction slides

Additional material:
Stuart Russell, Provably Beneficial AI,
http://home.mit.bme.hu/~tade/reports-on-ai-future/russell-ijcai17-pbai.pptx

Lecture 2:

Uninformed search algorithms
Example

Additional materials:

A_pigeon_solves_the_classic_box-and-banana_problem
https://www.youtube.com/watch?v=mDntbGRPeEU

Are_crows_the_ultimate_problem_solvers
https://www.youtube.com/watch?v=AVaITA7eBZE

Lecture 3:

Informed search

Additional materials:

A zip file containing:
Greedy Search example, A* example (A* contours), Hill climbing search example,
Recursive Best-first Search example, Unifrom cost search example, Simulated annealing

Lecture 4:

Adversarial search

Additional materials:

Genetic algorithms

Lecture 5:

Constraint satisfaction problems (CSP)

Additional materials:

Arc consistency checking

Lecture 6:

Propositional logic, inference

(See the bottom of the page for slides L4-L6)

Lecture 7:

First-order logic

(See the bottom of the page for slide L8)

Lecture 8:

Uncertainty, Bayesian networks, probabilistic inference

(See the bottom of the page for slides L10, L11, L12)

Lecture 9:

Decision theory, decision networks, recommendation systems

(See the bottom of the page for slides L12, L13)

Lecture 10:

Midterm preparation

Lecture 11:

Recommendation systems

AI_collab-filtering-tutorial_2019.ppt

AI_eng_matrix_factorization_2019.pptx

Lecture 12:

Supervised learning, decision trees
AI_2017_Learning_v1.pptx

Lecture 13:

Neural networks
VIMIAC10-2019-Introduction_to_Neural_Networks.pptx

Lectures 14-15:

Cooperative agents
AI_Cooperative-Agent-Systems-L5-2019.pdf

Lecture 16:

Distributed learning
AI_Learning-in-Agent-Systems-L6-2019.pdf

Lecture 17:

Semantic technologies, description logic

Lecture 18:

Artificial general intelligence

Lecture 19:

Endterm preparation - 9th December 2019, Monday 14:15-16:00, Room IE.224.
VIMIAC10-2019-12-ZH2-Tests_Tasks_EN.pptx

Book:

S. Russell and P. Norvig Artificial Intelligence: A Modern Approach Prentice Hall, 2003, Second edition or higher.

Suggested reading:

Attached files: 

Introduction (2019)

Lecture1: Introduction

L2-3: Problem solving with search: uninformed search (Ch3.1,3.3,3.4)

L4: Problem solving with search: informed search (Ch4.1,4.2)

L5: Syntacs and semantics of logic (Ch:7.1,7.3,7.4)

L6: Truth and proofs: theorem provers (Ch:7.5)

L7: Basics of probability theory, probabilistic logic

L8: From propositional logic to first-order logic (Ch:8.2,9.1,10.1,10.2,10.6)

L9: Background for 1st major homework

L10: Simple probabilistic models

L11-L12: Bayesian networks

L12: Structural inference of independencies

L12-L13: Decision theory and decision networks

BayesCube manual

L13: Causal inference

++: KM, JP: Graphical Models for Causal Inference (UCLA)

++: JP: Causal inference in statistics

L14: Simple decisions, value of information

L15: Inference in BNs: Markov chains, Hidden Markov Models

Search algorithm animations

Informed search examples

AI_BMEMIT_ProbBN_2019.pptx

AI_collab-filtering-tutorial_2019.ppt

AI_eng_matrix_factorization_2019.pptx

Cooperative and Competetive agents - 2019

Learning - from a single agent to the Multi Agent Systems - 2019

Single agent Q-learning demo

VIMIAC10-2019-Introduction_to_Neural_Networks.pptx