IdCL23

Language:

Italian
Textbooks:

Machine Learning: A multistrategy approach. Author: Tom Mitchell

Hands-On Machine Learning with Scikit-Learn, Keras, and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent Systems. Author: Aurélien Géron. O'Reilly
Learning objectives:

The aim of the course is to sensitize the engineer to issues related to artificial intelligence and machine learning, providing an overview of the main notions that can be of help in the project management.
Prerequisite:
Teaching methods:

Frontal lesson with the use of power point or PDF presentations.
Exam type:

Open choice questions on the topics of the course.
Sostenibilità:
Further information:

Lessons will be given face to face, except for specific cases that must be properly discussed with the teacher.

Introduction to Machine Learning. Data preprocessing. The problem of learning. Classification, regression and clustering. Deep learning. Exercises with the main Python libraries.

Introduction to Machine Learning. The knowledge discovery process. Data preprocessing. The problem of learning. Supervised and unsupervised learning. Batch, incremental, natural learning. Reinforcement learning. Problems related to learning: parameter tuning, performance evaluation, training, validation and testing, the problem of overfitting. Classification: decision trees. Linear and logistic regression. Artificial neural networks. Clustering: K-Means. Agglomerative and density-based clustering (DBSCAN). Representation learning. Convolutional Neural Network. Recurrent Neural Network. Long Short-Term Memory Network. Introduction to Generative Artificial Intelligence and Large Language Models.
Introduction to the Python language. Python and the Jupyter Notebook environment. The Sikit-learn environment: exercises on supervised classification.
The TensorFlow environment: exercises on Convolutional Neural Network and Recurrent Neural Network.