Important notice
The course guide is provisional.
The PDF version of the course guide may take a few days to become available in the DDD.
Machine Learning and Artificial Intelligence: Application to Materials' Discovery
Code: 45737Credits: 3
| Degree programme | Type | Course |
|---|---|---|
| Applied Nanoscience: From Materials to Devices | OP | 1 |
Contact lecturer
- Name :
- Marta Gonzalez Silveira
- Email :
- marta.gonzalez@uab.cat
Teaching staff
- Manel del Valle Zafra
Teaching staff (external to UAB)
- Andrés Henao Aristizábal
Group languages
You can consult this information at the end of the document.
Prerequisites
Knowledge of materials characteristic features and (recommended) some knowledge of Python programming language but not essent
Objectives
The present course aims to:
- Introducing students to machine learning for the modeling of properties of nanomaterials
- To familiarize with analysis, visualization and modeling of data from nanomaterials databases
- Introducing concepts of data mining and artificial intelligence in the context of new nanomaterials discovery and property predictions
Learning outcomes
- CA17 (Validate pattern recognition, supervised and unsupervised, in image processing and analysis.) Validate pattern recognition, supervised and unsupervised, in image processing and analysis.
- KA15 (Recognise the appropriate tools in determining the properties of functional nanomaterials.) Recognise the appropriate tools in determining the properties of functional nanomaterials.
- KA16 (Identify the use of unsupervised generic approaches in the determination of specific nanomaterial parameters.) Identify the use of unsupervised generic approaches in the determination of specific nanomaterial parameters.
- SA19 (Use standard machine learning tools in the implementation of a multiple regression model for different quantities that allow the generation of parameters for different types of nanomaterials.) Use standard machine learning tools in the implementation of a multiple regression model for different quantities that allow the generation of parameters for different types of nanomaterials.
- SA20 (Analyse large volumes of material data using different databases.) Analyse large volumes of material data using different databases.
- SA21 (Interpret the capabilities of machine learning techniques and their fundamental limitations based on the terms that the model incorporates.) Interpret the capabilities of machine learning techniques and their fundamental limitations based on the terms that the model incorporates.
Contents
The syllabus of the subject is subdivided into the following lessons:
- Introduction to machine learning for nanoscience and nanomaterials.
- Tools for prediction of material properties. Multivariate Regression algorithms. QSAR.
- Pattern recognition: unsupervised learning for material classification. Principal component analysis. K-means.
- Supervised learning. Classification algorithms. Decision trees and
- Databases and visualization. Use of python APIs for data mining.
- Use of the Computational 2D Materials database (C2DB).
- The Materials project database. Analysis tools to inspire and design novel materials.
- The Jarvis database. An infrastructure designed to automate materials discovery and optimization.
- Optimization and interpretation of obtained models. Hyperparameter tuning and exploration of factors influence using SHAP.
Learning activities and methodology
| Title | Hours | ECTS | Learning outcomes |
|---|---|---|---|
| Collaborative assignments of final study case | 25 | 1 | CA17, SA20, SA21 |
| Lecture sessions | 8 | 0.32 | KA15, SA21 |
| Problem-solving and practical sessions | 10 | 0.4 | CA17, KA16, SA19, SA20 |
| Individual assignments of case studies | 30 | 1.2 | CA17, KA15, KA16, SA19, SA20 |
The contents of this subject will be provided by presentations by the assigned professors, and by hands-on work in the computer room of the Faculty of Sciences, with suèrvision of instructors. Presentation slides will be made available through the Moodle page of the course. Along the progress of the subject, individual assignments related to materials discovery and predictions of some of their specific characteristics and properties, taken from a publicly offered list of case studies.will make the student to deepen in the speciality. Special attention will be placed in exercising data mining from established databases in the field. A more elaborated case, worked collaboratively, for example in couples, will serve to achieve the global perspective and application of achieved abilities.
Use of AI
For this subject, the use of Artificial Intelligence (AI) technologies is permitted exclusively in support tasks, such as bibliographic or information searches, text correction or translations. In the event that AI is used, the student must clearly identify which parts have been generated with this technology, specify the tools used and include a critical reflection on how these have influenced the process and the final result of the activity. The lack of transparency in the use of AI in an assessable activity will be considered a lack of academic honesty and may lead to a partial or total penalty in the grade of the activity.
Assessment
Continuous assessment activities
| Title | Weight | Hours | ECTS | Learning outcomes |
|---|---|---|---|---|
| Quizzes | 30% | 1 | 0.04 | CA17, KA15, KA16, SA19, SA21 |
| Individual assignments | 30% | 0.75 | 0.03 | CA17, KA15, KA16, SA19, SA20, SA21 |
| Final assignment | 40% | 0.25 | 0.01 | CA17, KA15, KA16, SA19, SA20, SA21 |
The assessment will consist of the following components:
(i) Quizzes (multiple choice questions), using the virtual campus - this is to motivate students to review the concepts (30%)
(ii) 3 individual assignments (one for each of the large databases indicated). To deliver via virtual campus (30%)
(iii) 1 final assignment, of greater scope, done in pairs and which they will have to defend orally (40%).
Any irregularity committed during an assessment activity (academic fraud, plagiarism, or the improper use of AI—unless such use is expressly authorized in the course syllabus) that could lead to a significant change in the grade will result in a grade of 0 for that activity. If the course syllabus stipulates that achieving a minimum grade in that specific assessment activity is a mandatory requirement for passing the course, or if multiple irregularities occur across assessment activities for the same course, the final course grade will be 0. Furthermore, disciplinary proceedings may be initiated against any student who commits such irregularities.
Bibliography
Chris Albon, Machine learning with Python cookbook: practical solutions from preprocessing to deep learning.
O’Reilly Media, 2018.
Eric Mathes, Python crash course : a hands-on, project-based introduction to programming.
No Starch Press, Inc., 2019.
Software
Python (v.3.14) and the corresponding libraries and APIs necessary for the development of the materials.
The software for the course will be available in the computer classroom of the Faculty of Sciences.
Course groups and languages
The information provided is provisional until November 30. After this date, you will be able to consult the language of each group through this link. To access the information, you will need to enter the course CODE
| Type of teaching | Group | Language | Semester | Shift |
|---|---|---|---|---|
| (TEm) Theory (master) | 1 | English | first semester | afternoon |