Applied Artificial Intelligence

Year:
2nd year
Semester:
S1
Programme main editor:
(I2CAT)
Onsite in:
Remote:
ECTS range:
3 ECTS

Professors

img
Professors
Daniele Miorandi
AU

Prerequisites:

  • Working knowledge of Python.
  • Working knowledge of standard Python ML/DL libraries (sklearn, pytorch).
  • Understanding of core ML/DL concepts (model, methods, training, performance evaluation, overfitting etc.).

Pedagogical objectives:

This course introduces students to the practical applications of artificial intelligence (AI) across various industrial domains. Through a combination of lectures, hands-on projects, and case studies, students will gain the knowledge and skills necessary to develop and deploy AI solutions to solve real-world problems. Topics covered will include AI models and methods, practices for operating ML-powered solutions, usage of LLMs and ethical considerations in AI.

Evaluation modalities:

Project work; a project assignment to perform after the STC execution will also be evaluated.

Description:

The course covers the following topics:

  • Introduction to Applied Artificial Intelligence
    • Overview of AI applications in different industries.
    • Ethical considerations and responsible AI practices.
  • Brief recap: Foundations of Machine Learning/Deep Learning
    • Supervised, unsupervised, and reinforcement learning.
    • Classification, regression, forecasting.
    • Training, fine tuning and overfitting.
    • Performance evaluation of ML/DL models.
  • Domains: computer vision, natural language processing, sequential data.
  • AI Deployment and Integration
    • Model deployment strategies.
    • Introduction to cloud-based AI services.
    • Integrating AI models into applications and systems.
  • Case Studies and Project Work
    • Analysis of real-world AI applications across industries.
    • Team project: Design and implementation of an AI solution for a specific use case.
  • Project Presentation and Wrap-Up.
    • Final project presentations by student groups.

Reflection on key learnings and future directions in applied AI.

Required teaching material

Slides will be shared with students together with sample code whenever required.

Teaching volume:
lessons:
15 hours
Exercices:
Supervised lab:
Project:
15 hours

Devices:

  • Laboratory-Based Course Structure
  • Open-Source Software Requirements