Vincenzo DEUFEMIA | ARTIFICIAL INTELLIGENCE
Vincenzo DEUFEMIA ARTIFICIAL INTELLIGENCE
cod. 0522500093
ARTIFICIAL INTELLIGENCE
| 0522500093 | |
| DIPARTIMENTO DI INFORMATICA | |
| EQF7 | |
| COMPUTER SCIENCE | |
| 2020/2021 |
| YEAR OF COURSE 2 | |
| YEAR OF DIDACTIC SYSTEM 2016 | |
| PRIMO SEMESTRE |
| SSD | CFU | HOURS | ACTIVITY | |
|---|---|---|---|---|
| INF/01 | 9 | 72 | LESSONS |
| Objectives | |
|---|---|
| THE MAIN GOAL OF THE COURSE IS TO PROVIDE THE STUDENTS WITH THE THEORETICAL AND PRACTICAL FOUNDATIONS FOR THE ANALYSIS, DESIGN, AND IMPLEMENTATION OF INTELLIGENT SYSTEMS. THE MAIN SKILLS THAT WILL BE ACQUIRED ARE: • INTELLIGENT AGENTS; • SEARCH STRATEGIES FOR PROBLEM SOLVING; • KNOWLEDGE REPRESENTATION AND INFERENCE METHODS, WITH PARTICULAR EMPHASIS ON THOSE BASED ON FIRST ORDER LOGIC AND RELATED INFERENCE METHODS; • REPRESENTATION OF UNCERTAIN KNOWLEDGE AND PROBABILISTIC INFERENCE METHODS, WITH SPECIAL EMPHASIS ON BAYESIAN NETWORKS; • LEARNING TECHNIQUES AND NATURAL LANGUAGE PROCESSING; • RECOMMENDING STRATEGIES. THE MAIN SKILLS (I.E., THE ABILITY TO APPLY THE ACQUIRED KNOWLEDGE) WILL BE: • TO ANALYSE PROBLEMS SOLVABLE THROUGH ARTIFICIAL INTELLIGENCE TECHNIQUES; • TO IDENTIFY THE MOST SUITABLE ARTIFICIAL INTELLIGENCE TECHNIQUES FOR SOLVING A PROBLEM, AMONG THOSE STUDIED DURING THE COURSE; • TO IDENTIFY SOFTWARE TECHNOLOGIES SUPPORTING THE ARTIFICIAL INTELLIGENCE TECHNIQUES CHOSEN TO SOLVE A PROBLEM; • TO DESIGN INTELLIGENT SYSTEMS TO SOLVE REAL PROBLEMS. |
| Prerequisites | |
|---|---|
| STUDENTS SHOULD BE FAMILIAR WITH FUNDAMENTALS OF STATISTICS AND DATA ANALYSIS, NEURAL NETWORKS AND MACHINE LEARNING. |
| Contents | |
|---|---|
| AFTER INTRODUCING THE BASIC CONCEPTS OF ARTIFICIAL INTELLIGENCE, INCLUDING RESEARCH BACKGROUNDS, THE COURSE WILL PROVIDE THE BASIC NOTIONS OF INTELLIGENT AGENTS, SINCE THEY ARE PREPARATORY TO THE FOLLOWING TOPICS ON WHICH THE COURSE WILL FOCUS: PROBLEM SOLVING • SOLVING PROBLEMS BY SEARCHING • BEYOND CLASSICAL SEARCH • ADVERSARIAL SEARCH KNOWLEDGE AND REASONING • LOGICAL AGENTS • FIRST-ORDER LOGIC • INFERENCE IN FIRST-ORDER LOGIC • KNOWLEDGE REPRESENTATION UNCERTAIN KNOWLEDGE AND REASONING • QUANTIFYING UNCERTAINTY • PROBABILISTIC REASONING • BAYESIAN NETWORKS • INFERENCE TECHNIQUES BASED ON BAYESIAN NETWORKS • SIMPLE DECISIONS LEARNING • LEARNING FROM EXAMPLES • KNOWLEDGE IN LEARNING • RECURRENT NEURAL NETWORKS • DEEP LEARNING • REINFORCEMENT LEARNING RECOMMENDER SYSTEMS • CONTENT-BASED AND COLLABORATIVE FILTERING • LATENT FACTOR MODELS: THE BELLKOR SYSTEM NATURAL LANGUAGE PROCESSING • N-GRAM MODELS AND TAGGING • SYNTACTIC AND SEMANTIC PARSING • WORD SENSE DISAMBIGUATION • DEEP LEARNING FOR NLP |
| Teaching Methods | |
|---|---|
| THE COURSE INCLUDES 72 HOURS OF LECTURES BETWEEN FRONTAL LESSONS AND CLASSROOM EXERCISES (9 CFUS), AIMING TO INTRODUCE CONCEPTS AND TO DEVELOP ABILITIES TO SOLVE PROBLEMS BY USING ARTIFICIAL INTELLIGENCE TOOLS AND TECHNIQUES. |
| Verification of learning | |
|---|---|
| THE ACHIEVEMENT OF THE COURSE OBJECTIVES IS CERTIFIED BY MEANS OF AN EXAM, WHOSE FINAL GRADE IS EXPRESSED ON A SCALE OF 30. THE EXAM CONSISTS OF THE DEVELOPMENT OF A WRITTEN TEST AND AN ORAL EXAM. TO ACCESS THE ORAL EXAM, STUDENTS MUST PASS THE PRACTICAL TEST WITH A MINIMUM GRADE OF 18/30. THE GOAL OF THE WRITTEN TEST IS TO VERIFY THE ABILITY OF THE STUDENTS TO USE THE AI TECHNIQUES PRESENTED DURING THE COURSE. THE ORAL EXAM CONSISTS OF AN INTERVIEW WITH QUESTIONS ON THE THEORETICAL AND METHODOLOGICAL CONTENTS TAUGHT DURING THE COURSE, AIMING TO ASSESS THE LEVEL OF KNOWLEDGE AND UNDERSTANDING AS WELL AS THE ABILITY TO EXPOSE CONCEPTS. GENERALLY, THE FINAL GRADE AVERAGES THE PROJECT AND ORAL EXAMINATION. THE STUDENT HAS THE OPPORTUNITY TO CARRY OUT A PROJECT TO INCREASE THE FINAL GRADE. THE PROJECT CAN BE CARRIED OUT INDIVIDUALLY OR IN GROUPS OF UP TO 3 STUDENTS AND CONSISTS OF SOLVING A PROBLEM WITH ARTIFICIAL INTELLIGENCE TECHNIQUES. STUDENTS CAN SUBMIT A PROJECT’S THEME TO THE TEACHER FOR APPROVAL, OR ALTERNATIVELY, CHOOSE FROM A RANGE OF PROPOSALS PROVIDED BY THE TEACHER. AT THE END OF THE PROJECT, STUDENTS MUST DELIVER A TECHNICAL REPORT CONTAINING THE PROJECT DOCUMENTATION, AND A POWERPOINT PRESENTATION OF THE PROJECT, LASTING ABOUT 30 MINUTES. |
| Texts | |
|---|---|
| S. J. RUSSELL, P. NORVIG, INTELLIGENZA ARTIFICIALE. UN APPROCCIO MODERNO, VOLUME 1 (3/ED, 2010) E VOLUME 2 (2/ED, 2005), PEARSON EDUCATION ITALIA OTHER BOOKS: C. M. BISHOP: “PATTERN RECOGNITION AND MACHINE LEARNING”, SPRINGER SCIENCE, NEW YORK, 2006 I. GOODFELLOW, Y. BENGIO, A. COURVILLE, “DEEP LEARNING”, MIT PRESS, 2016. JURE LESKOVEC, ANAND RAJARAMAN, JEFFREY D. ULLMAN, “MINING OF MASSIVE DATASETS”, 2^ EDITION, CAMBRIDGE UNIVERSITY PRESS, 2014. D. JURAFSKY AND J. MARTIN. SPEECH AND LANGUAGE PROCESSING, PRENTICE HALL, 2009. |
| More Information | |
|---|---|
| COURSE ATTENDANCE IS STRONGLY RECOMMENDED. STUDENTS MUST BE PREPARED TO SPEND A FAIR AMOUNT OF TIME IN THE STUDY OUTSIDE OF LESSONS. FOR A SATISFACTORY PREPARATION STUDENTS NEED TO SPEND AN AVERAGE OF TWO HOURS OF STUDY TIME FOR EACH HOUR SPENT IN CLASS. HALF OF THIS TIME IS NECESSARY TO ACQUIRE AN ADEQUATE FAMILIARITY WITH SOFTWARE TOOLS FOR DEVELOPING INTELLIGENT SYSTEMS. COURSE MATERIALS WILL BE AVAILABLE FOR DOWNLOAD FROM THE DEPARTMENTAL E-LEARNING PLATFORM HTTP://ELEARNING.INFORMATICA.UNISA.IT/EL-PLATFORM/ CONTACTS PROF. VINCENZO DEUFEMIA DEUFEMIA@UNISA.IT |
BETA VERSION Data source ESSE3 [Ultima Sincronizzazione: 2022-05-23]
