The course is offered in the first semester of the 2nd year. The course is taught in English. The main objective of the course is to learn how to build applications based on an artificial intelligence technology. The topics of the course range from the design and development, management and communication of the project leading to the finalization of real-word applications. The course has a three-fold structure: concepts, tools, and labs. The goal of this course is to let students work on a long running project and learn how to manage all project steps (identification of user needs, problem statement, task assignment, design and implementation of the application, testing, milestones management, writing of intermediate and final reports, result communication). Laboratory activities will expose students with first-hand experience with data science and artificial intelligence technologies in collaboration with international companies and applied research institutes.

- Knowledge of first-hand computational tools to build applications based on artificial intelligence technologies - Knowledge of the design of best practices and tools - Knowledge of management strategies and tools - Knowledge of communication tools and skills - Knowledge of the solution impact s - Hands on experience with an application that utilizes real user data offered by companies and research institutes

Statistics Data mining Machine learning and Deep learning Python language Relational, NOSQL, graph databases

Lectures (26 hours) - Building an artificial intelligence application (1.5h) - Introduction to project pillars: management, design, development and communication (1.5h) - Model and Data-centric projects (1.5h) - Foundation models (1.5) - Retrieval Augumented Generation (1.5h) - Artificial intelligence ethics (1.5h) - Impact of a project and SGDs (1.5h) - Project tools (14h) - Management: GANTT, Work breakdown structure, work packages and tasks, milestone - Design: User personas, stakeholder map, functional requirements - Development: - Foundation models: Large language models and vision language models - Domain adaptation and downstream tasks - Retrieval Augumented Generation implementation - Version control and testing - Communication: Presentation, Technical Paper, Deliverable - Success stories of past projects (1.5h) Laboratory activities (54h) - Project proposals (1.5h) - User-centred application (3h) - Stakeholder maps and user personas - User journey - Use of SDKs and REST APIs of commercial neural models with prompt engineering (6h) - Use of Ollama with open source models (3h) - Development of the team project (40.5)

The course is structured in three folds: 1) Introduction to the concepts to perform a project 2) Introduction to the tools to put in place the concepts 3) Laboratory sessions for the execution of the projects and meetups with the company key resources (project managers and project leaders) to successfully execute the assigned projects.

Copies of the slides used during the lectures will be made available. All teaching material is downloadable from the teaching portal. Reference books: - Machine Learning Yearning, by Andrew Ng - Data Science from Scratch, Joel Grus - Harvard Business Review Project Management Handbook: How to Launch, Lead, and Sponsor Successful Projects, by Antonio Nieto-Rodriguez - Oxford Guide to Effective Writing and Speaking: How to Communicate Clearly, by John Seely - The Design of Everyday Things: Revised and Expanded Edition, by Donald Norman - Noessel C. Designing Agentive Technology. AI That Works for People. Rosenfeld, 2013 - Proposal for a Regulation laying down harmonised rules on artificial intelligence, European Commission, 2021

Slides; Libro di testo; Esercitazioni di laboratorio;

Modalità di esame: Prova orale obbligatoria; Elaborato progettuale in gruppo;

Exam: Compulsory oral exam; Group project;

... Exam: Compulsory oral exam; Group project The exam includes a mandatory oral part (20% of the overall mark), and the evaluation of the team project assigned during the course (80% of the overall mark). Learning objectives assessment The oral exam covers all the theoretical concepts introduced during the course and will assess - Knowledge of first-hand computational tools to build applications based on artificial intelligence technologies - Knowledge of the design of best practices and tools - Knowledge of management strategies and tools - Knowledge of communication tools and skills - Knowledge of the solution impact - Hands on experience with an application that utilizes real user data offered by companies and research institutes The team project and the delivered report will assess - Ability to design, implement and evaluate a complete project - Ability to use first-hand computational tools to address projects - Ability to use management tools - Ability to use communication tools Exam structure and grading criteria The team project consists in managing, designing and implementing an artificial intelligence solution utilizing a data science approach. Projects are assigned by companies or applied research institutes. The team project is assigned in the first half of the course and its report must be delivered before the end of the course. The team project is also characterized by intermediate milestones. Its score is valid for the entire academic year. The evaluation of the team project is based on the performance and accuracy of the proposed solution, in terms of standard quality measures (e.g., prediction accuracy) and completeness (i.e., in depth analysis of each phase of the designed process and motivation for selecting given techniques and algorithms). The clearness and completeness of the delivered reports will also be considered. The oral exam covers all the theoretical parts of the course. The score is based on the completeness and clarity of the answers. The maximum grade for the team project is 32. The maximum grade for the oral part is 32. The final grade is given by weighted average of the two parts (0.8*grade team project + 0.2*grade oral part). The exam is passed if the grade of the team project is greater than or equal to 18 and the grade of the oral part is greater than or equal to 18.

Gli studenti e le studentesse con disabilità o con Disturbi Specifici di Apprendimento (DSA), oltre alla segnalazione tramite procedura informatizzata, sono invitati a comunicare anche direttamente al/la docente titolare dell'insegnamento, con un preavviso non inferiore ad una settimana dall'avvio della sessione d'esame, gli strumenti compensativi concordati con l'Unità Special Needs, al fine di permettere al/la docente la declinazione più idonea in riferimento alla specifica tipologia di esame.