Unit INTRODUCTION TO ARTIFICIAL INTELLIGENCE
- Course
- Informatics
- Study-unit Code
- A000701
- Curriculum
- In all curricula
- Teacher
- Valentina Poggioni
- Teachers
-
- Valentina Poggioni
- Hours
- 47 ore - Valentina Poggioni
- CFU
- 6
- Course Regulation
- Coorte 2018
- Offered
- 2020/21
- Learning activities
- Caratterizzante
- Area
- Discipline informatiche
- Academic discipline
- INF/01
- Type of study-unit
- Opzionale (Optional)
- Type of learning activities
- Attività formativa monodisciplinare
- Language of instruction
- Italian
- Contents
- Introduction to artificial intelligence.Turing's Test. Agent-reasoner approach. Agent Models. State Space Search. Uninformed search. Informed Heuristic search, A*. Properties of heuristics. Distributed Agents. Fundamentals of logics. Two players games: minimax.
Data Mining and Machine Learning. Supervised approach: data classification. Introduction to neural network. Model evaluation methods and measures. Building of training and test sets. Results analysis. - Reference texts
- Stuart Russel, Peter Norvig, Artificial Intelligence: A Modern Approach, Global Edition - Pearson - 2016
Pang-Ning Tan, M. Steinbach, A. Karpatne, V. Kumar - Introduction to data mining - Pearson - 2019 - Educational objectives
- The student will acquire fundamental concepts and basic notions of artificial intelligence systems and agents based models. The student will know main algorithms for uninformed and heuristics state space search. He/she will be able to model and implement an agent based system as state space search problem. He/she know the basic schema of two players games and in particular the minimax algorithm. The student will learn the main techniques and algorithms for data mining and in particular for data classification. She/he will be able to design, implement and test a supervised learning system using different algorithm, included neural networks.
- Prerequisites
- Basic knowledge on Python programming.
- Teaching methods
- Face to face lessons in room and laboratory.
- Other information
- https://unistudium.unipg.it
- Learning verification modality
- Oral exam and project development. Partial exams during the course.
- Extended program
- Introduction to artificial intelligence.Turing's Test. Agent-reasoner approach/rational-human. Agent Models: reactive agent, simple agent with state, planning agent, utility based agent. State Space Search: modelling problems. Uninformed search DFS, BFS, limited depth, uniform cost,. Informed Heuristic search, greedy, A*. Space/Time complexity of algorithms, equivalent branching factor. Properties of heuristics. Distributed Agents: swarm behaviour, emergent properties. Fundamentals of logics.
The Knowledge Discovery process in Databases (KDD). Introduction to machine learning.
Classification: decision tree (attributes and algorithms); NN classifiers; Naive Bayes classifiers; neural networks classifiers.
Techniques and measures for model evaluation. Building and analysis of training and test sets.