Caricamento in corso...
Introduction to scientific machine learning
01HWXIW
A.A. 2024/25
Course Language
Inglese
Degree programme(s)
Doctorate Research in Ingegneria Aerospaziale - Torino
Course structure
| Teaching | Hours |
|---|---|
| Lezioni | 20 |
Lecturers
| Teacher | Status | SSD | h.Les | h.Ex | h.Lab | h.Tut | Years teaching |
|---|---|---|---|---|---|---|---|
| Magri Luca | Professore Ordinario | IIND-01/F | 20 | 0 | 0 | 0 | 2 |
Co-lectures
Context
| SSD | CFU | Activities | Area context | *** N/A *** |
|---|
Presentazione degli algoritmi piu' utilizzati in ingegneria, industria, e scienza che sono basati su machine learning. Il corso e' un introduzione a machine learning for science. Gli studenti impareranno tematiche teoriche e pratiche di machine learning con attenzione a scientific ML. Conoscenza pregressa in machine learning non e' richiesta.
This course introduces the most common Machine Learning (ML) algorithms deployed in the engineering, science, and industry. Students will acquire theoretical and practical understanding of ML models with a focus on scientific machine learning. The course is an introductory course to scientific ML. No prior knowledge in machine learning is required.
Laurea magistrale (o equivalente) in ingegneria, e/o matematica, e/o fisica, e/o informatica, e/o equivalente.
MEng/MSc Degree (or equivalent) in engineering, and/or maths, and/or physics, and/or computer science, and/or equivalent.
Fondamenti di artificial intelligence (AI) e machine learning (ML); richiami di ottimizzazione non-convessa, regressione/classificazione e backpropagation, reti neurali (feedforward, convolutional, recurrent), unsupervised learning.
Introduction to AI and ML; revision of non-convex optimisation, regression/classification and backpropagation, neural networks (feedforward, convolutional, recurrent), unsupervised learning.
Modalità mista
Mixed mode
Test a risposta multipla
Multiple choice test
P.D.1-1 - Febbraio
P.D.1-1 - February