INTRODUCTION TO MACHINE LEARNING - 21068-ENG

courses

ID:

21068-ENG

Dettaglio:

SSD: Data Processing Systems Duration: 48 CFU: 6

Located in:

DALMINE

Url:

Course Details:

COMPUTER SCIENCE AND ENGINEERING - 21-270/PERCORSO COMUNE Year: 3

Course Details:

COMPUTER SCIENCE AND ENGINEERING - 38-270/PERCORSO COMUNE Year: 1

COMPUTER SCIENCE AND ENGINEERING - 38-270/PERCORSO COMUNE Year: 2

Year:

2025

Date/time interval

Secondo Semestre (23/02/2026 - 06/06/2026)

Course Objectives

By the end of this course, students will understand key concepts and algorithms in machine learning (ML). They will gain hands-on experience in implementing ML models using Python and relevant libraries, such as Scikit-Learn, and PyTorch. Furthermore, they will learn to evaluate and optimize machine learning models for different tasks.

Course Prerequisites

Basic knowledge of computer science algorithms, linear algebra and programming (Python) is recommended.

Teaching Methods

Slides will be used for instruction. Slides will be provided to students in advance and made available on MS Teams group. Lab exercises will be conducted using Python.

Assessment Methods

Students will be evaluated through a written exam, which will include theory-based questions. The final grade will be assigned on a 30-point scale.

Introduction to Machine Learning: Overview of machine learning paradigms, key applications, and differences between supervised, unsupervised, and reinforcement learning.
Supervised Learning: Understanding labeled data, regression vs. classification, and key algorithms such as linear regression and logistic regression.
Nearest Neighbors: Introduction to k-Nearest Neighbors (k-NN) algorithm, distance metrics, and decision boundaries.
Decision Trees and Random Forests: Explanation of decision tree learning, entropy, information gain, and ensemble methods like bagging and random forests.
Kernel Methods: Introduction to kernel trick, Support Vector Machines (SVM), and their application in high-dimensional space.
Deep Neural Networks: Overview of deep learning, including feedforward networks, convolutional neural networks (CNNs) for image processing, and recurrent neural networks (RNNs) for sequence data.
Unsupervised Learning: Exploring clustering methods (K-means, hierarchical clustering) and dimensionality reduction techniques (PCA, t-SNE).
Generative Models: Introduction to generative adversarial networks (GANs), variational autoencoders (VAEs), Autoregressive Models and Diffusion Models for generating synthetic data.
Reinforcement Learning: Fundamentals of reinforcement learning, Markov decision processes (MDPs), Q-learning, and policy gradient methods.