Artificial Intelligence and Machine Learning

Course objectives

General objectives: Knowledge of main application scenarios in high-dimensional data analysis. Knowledge and understanding of main algorithms and approaches to analyze high dimensional data. Knowledge of main tools to implement them. Understanding of theoretical foundations underlying main techniques of analysis Ability to implement the aforementioned algorithms, approaches and techniques and to apply them to specific problems and scenarios. Knowledge of main evaluation techniques and their application to practical scenarios. Specific objectives: Ability to: - identify the most suitable techniques to address a data analysis problem where data dimensionality is a concern; - implement the proposed solution, identifying the most appropriate design and implementation tools, among available ones; - Design and implement experiments to evaluate proposed solutions in realistic settings; Knowledge and understanding: - knowledge of main application scenarios; - knowledge of main techniques of analysis; - understanding of methodological and theoretical foundations of main analysis techniques; - knowledge and understanding of main evalutation techniques and corresponding performance indices Apply knowledge and understanding: - being able to translate application needs into specific data analysis problems; - being able to identify aspects of the problem for which data dimensionality might play a critical role; - being able to identify the most suitable techniques and tools to address the aforementioned problems; - being able to estimate in advance, at least qualitatively, the degree of scalability of proposed solutions; Critical and judgment skills: Being able to evaluate, also experimentally, the effectiveness and efficiency of proposed solutions Communication skills: Being able to effectively describe the requirements of a problem and provide to third parties the relative specifications, design choices and the reasons underlying these choices. Learning ability: The course will facilitate the development of skills for the independent study of topics related to the course. It will also allow students to identify and critically examine material contained in advanced manuals and/or scientific literature, allowing them to face new application scenarios and/or apply alternative techniques to known ones.

Channel 1
FABIO PATRIZI Lecturers' profile

Program - Frequency - Exams

Course program
Artificial Intelligence (6CFU) Introduction to Artificial Intelligence Propositional Logic Propositional formulas and knowledge-bases Evaluation (Model Checking), Satisfiability, Validity, Logical Implication Tableaux DPLL, SAT solvers First-Order Logic Evaluation in First-Order Logic Reasoning in First-Order Logic Tableaux Incomplete information and Conjunctive Queries Reasoning about Actions Modeling dynamics of the domain of interest Deliberating and executing actions Action Preconditions, Effects, the Frame Problem, Situation Calculus: Precondition Axioms, Successor State Axioms Situation tree Regression Executability of sequences of actions and Projection (querying a situation resulting from action sequences execution) Planning in Deterministic Domains Deterministic Planning Domains STRIPS, ADL, Planning Domain Description Language (PDDL) Transition Systems Planning by backward fixpoint computations Planning by forward search, Heuristics, Best-first, A* Planning in Nondeterministic Domains (FOND) Nondeterministic Planning Domains PDDL with oneof operator Game Theoretic View Nondeterministic Planning by backward fixpoint computations Nondeterministic Planning by Adversarial Search, Search in AND-OR Graphs Machine Learning (3CFU): Introduction to Machine Learning Basics on Probability (Review) Supervised Learning: Linear Classification Linear Regression Neural Networks Unsupervised Learning Reinforcement Learning
Prerequisites
Knowledge of object-oriented analysis, modeling and design, relational databases, and basic notions of probabilities, as acquired in previous courses.
Books
Artificial Intelligence: A Modern Approach, Global Edition, 4th Edition by Stuart Russell, Peter Norvig, Pearson 2020 (selected chapters). Reinforcement Learning: An Introduction, 2nd Edition by Richard S. Sutton and Andrew G. Barto. MIT Press, Cambridge, MA, 2018. (selected chapters). Deep Learning, by Ian Goodfellow, Yoshua Bengio and Aaron Courville, MIT Press, 2016. Knowledge in Action, by Raymon Reiter, MIT Press, 2001
Frequency
Attending is not mandatory but strongly encouraged.
Exam mode
The exam includes two parts: one written test about Artificial Intelligence and one Machine Learning project. The written part consists in 3/4 questions concerning: - modeling of a dynamic domain - reasoning about the modelled domain, e.g., regression or progression - reasoning about propositional and/or first-order knowledge (e.g., satisfiability, validity, logical implication of formulas./knowledge bases). The project part consists in the delivery and discussion of a Machine Learning project, where some of the techniques studied during the course are applied in combination.
Lesson mode
The course is taught in person. Lectures are recorded and made available asynchronously. Videos about labs and additional/focus lectures are made available.
  • Lesson code10599898
  • Academic year2024/2025
  • CourseEngineering in Computer Science
  • CurriculumSingle curriculum
  • Year1st year
  • Semester2nd semester
  • SSDING-INF/05
  • CFU9
  • Subject areaIngegneria informatica