- Oggetto:
- Oggetto:
DATA SCIENCE FOR CHEMISTS FROM MODELLING TO MACHINE LEARNING
- Oggetto:
DATA SCIENCE FOR CHEMISTS FROM MODELLING TO MACHINE LEARNING
- Oggetto:
Anno accademico 2025/2026
- Codice attività didattica
- CHI0191
- Docenti
- Marta Corno (Titolare degli insegnamenti)
Jacques Kontak Desmarais (Titolare degli insegnamenti) - Corso di studio
- Laurea magistrale in chimica
- Anno
- 1° anno
- Periodo
- Primo periodo
- Tipologia
- Affine o integrativo
- Crediti/Valenza
- 6
- SSD attività didattica
- CHIM/02 - chimica fisica
- Erogazione
- Tradizionale
- Lingua
- Inglese
- Frequenza
- Obbligatoria
- Tipologia esame
- Scritto più orale obbligatorio
- Oggetto:
Sommario insegnamento
- Oggetto:
Obiettivi formativi
The course outlines concepts of computer modelling and machine learning for the physical chemist. The student will learn about supervised and unsupervised learning algorithms for data analysis, as well as methods of classical and quantum-mechanical modelling in physical chemistry. The algorithms will be applied with hands-on sessions, employing the python programming language.
- Oggetto:
Risultati dell'apprendimento attesi
At the end of the course, the student will be able to:
1. Demonstrate knowledge and understanding of the fundamental concepts of computer modelling and machine learning, with specific reference to their application in physical chemistry.
2. Apply classical and quantum-mechanical modelling techniques to chemical systems and interpret their relevance within the context of physical chemistry research.
3. Select and implement appropriate supervised and unsupervised machine learning algorithms for the analysis of chemical and physical data sets, using Python-based tools.
4. Critically evaluate the strengths, limitations, and applicability of different modelling and machine learning methods in solving problems related to physical chemistry.
5. Communicate clearly and effectively the outcomes of computational and data-driven analyses, using appropriate scientific language, visualizations, and code documentation.
6. Pursue further learning and independently deepen knowledge in the fields of chemical modelling and data science through the use of scientific literature, online resources, and advanced software tools.- Oggetto:
Programma
Introduction (where do data come from?; what is Machine Learning?)
Modelling (What is so difficult?; The Schrodinger equation and the electron correlation problem)
Machine Learning (Models of Supervised and Unsupervised data classification and regression; Parametrizing the model: analytical solutions, the least-squares problem, gradient-based numerical optimizations)
- Oggetto:
Modalità di insegnamento
The course consists in frontal lessons, systematically complemented by hands-on sessions, where all concepts are applied by use of available Python-based tools after being formally presented and discussed. [total of 48 hours]
All classes will take place face-to-face (Lecture Hall TBD)
All didactic material will be published on the campusnet platform and available in a specific Google Drive folder (see "Note").
The course has a strong hands-on character so all students will need to bring a laptop to class.
All students are kindly asked to register for the course using the relevant item in the menu bar at the bottom of this page, in order to receive relevant communications about the course and what needs to be installed on your computer.- Oggetto:
Modalità di verifica dell'apprendimento
Written and oral exams (both mandatory).
The exam consists in two parts:
1) Written part
The written examination will be delivered in the form of a quiz consisting of 18 multiple-choice questions to be answered in 1 hour on students laptop. The questions will cover all topics addressed during the lectures.
2) Oral part
The oral examination will consist of a presentation of 6 slides, in English, prepared by the student, choosing a topic from the following list:
1. Multiscale MM/QM approaches to complex biointerfaces2. Coarse graining methods for large chemical systems3. How to approach big data in chemistry4. Molecular representations and Machine Learning for chemical exploration5. Methods of solution of linear least-square problems6. The BFGS algorithm7. Visualizing the principle component analysis8. Applications of neural networks to crystal structure prediction9. Choleski's decompositionBoth parts will be the same dayThe final mark will be calculated as an average of the marks for the written and oral parts.
Testi consigliati e bibliografia
- Oggetto:
Lecture notes and scripts by the teachers.
SHARED GOOGLE DRIVE FOLDER WITH LECTURES PDFS (prof. Corno): click here
Shared folder with Lecture PDFs (prof. Desmarais): link to be published
- Oggetto:
Note
Students with specific learning disabilities (SLD) or disabilities are requested to review the university's support (https://www.unito.it/servizi/lo-studio/studenti-e-studentesse-con-disabilita) and accommodation (https://www.unito.it/accoglienza-studenti-con-disabilita-e-dsa) procedures, particularly the procedures required for support during exams (https://www.unito.it/servizi/lo-studio/studenti-e-studentesse-con-disturbi-specifici-di-apprendimento-dsa/supporto).
- Registrazione
- Aperta
- Oggetto:
