Unit INTELLIGENT MODELS
- Course
- Informatics
- Study-unit Code
- A002038
- Curriculum
- Cybersecurity
- Teacher
- Alfredo Milani
- Teachers
-
- Alfredo Milani
- Hours
- 42 ore - Alfredo Milani
- CFU
- 6
- Course Regulation
- Coorte 2024
- Offered
- 2024/25
- Learning activities
- Caratterizzante
- Area
- Discipline informatiche
- Academic discipline
- INF/01
- Type of study-unit
- Obbligatorio (Required)
- Type of learning activities
- Attività formativa monodisciplinare
- Language of instruction
- English
- Contents
- 0 Introduction to AI
1 Agent models
2 State space search, adversarial search and automated planning
3 Reactive systems and multiagent models
4 Reinforcement learning agents
5 Interactive agents
6 Complex networks
7 AI network based models and applications
8 Ethical Aspects of AI - Reference texts
- Lectures notes made available on www.unistudium.unipg.it
Artificial Intelligence: A Modern Approach, 4th Edition
Stuart Russell and Peter Norvig
Pearson, 2020
Network Science
Albert Lazlo Barabasi
(available online http://networksciencebook.com/)
Reinforcement Learning: An Introduction,
Richard S. Sutton and Andrew G. Barto, Second Edition, MIT Press, 2018
(available online http://incompleteideas.net/book/RLbook2018.pdf ) - Educational objectives
- Expected learning outcomes.
Knowledge oriented goals
Knowledge of the main technique for modeling AI agent based problem domains
Knowledge of the main techniques for stata space search, uninformed, informed, local search based, automated reasoning and inference based, automated planning.
Reinforcement learning and policy optimization
Knowledge of modeling techniques for AI application domains characterized by complex networks
Knowledge of basic ethical questions concerning AI
Ability oriented goals
Ability to use the acquird knowledge to model, design and implement solutions to real application problems characterized by artificial agents and/or complex networks - Prerequisites
- Prerequisites for a fruitful acquisition of the contents of this course can be summarized in knowledge of computer science fundamentale, including algorithms, basic concepts of computational complexity, language grammars,basic concepts of logics, data structures, databases and concurrent and distributed system.
- Teaching methods
- In class lectures.
Lab sessions.
Discussion of case studies with the class. Continuous assessment and assignments during the semester.
Written and practical final exam. - Other information
- Elearning platform for student-lecturer interaction and online forum communication, upload of material and assignments, http://www.unistudium.unipg.it
- Learning verification modality
- The exams consists in final written exam and group project to be presented in written and oral form to the lecturer, during the oral presentation questions about topics in the course programme can be asked.
Written examination regards the main course topics. It consists in open ended question and and theoretical formal exercises asked on the course topics, and they can regard the analysis, modeling and solutions of problems in application domain by techniques of AI learned in the course.
The group project is assigned by the course lecturer on application of AI to real problems by focusing on techniques presented in the coursse.
The project includes a final report and an oral presentation by the participants which is part of the exam assessment. Purpose of the project is also to acquire practical experience and attitude to teamwork facing a real problem.
Ongoing assignments undertaken during the course can exhinnerate from all or part of the final written exam and are reserved to students attending the classes.
For information about services for students with disabilities or and/or Specific Learning Disorders (SLD) visit page http://www.unipg.it/disabilita-e-dsa - Extended program
- 0-Introduction to AI
Historical, current and future perspective
1-Agent models,Autonomous agents
Reflexive, state based, inference based, learning agents,
2-State space search, adversarial search and automated planning
State space search model, non informed, informed search, local search,
adversarial search, automated planning, logic based actions representation, PDDL
3-Reactive systems and multiagent models
Cellular automata, strategy driven agents, behavioural agents, emerging collective behaviours
4-Reinforcement learning agents
Markov Decision Processes, Policy evaluation, Q-learning, Integrating planning and learning
5-Interactive agents
interaction, chatbot, basics for NLP based systems, affective computing
6-Complex networks
Graph rheory, random and scale free networks, Barabasi-Albert model, metrics, communities
7-AI network based models and applications
knowledge networks, social networks, information diffusion, network agents, link prediction
8-Ethical Aspects of AI - Obiettivi Agenda 2030 per lo sviluppo sostenibile
- Quality Education
Industry , Innovation, Infrastrucures
Sustainable cities and communities