Syllabus

LEARNING OUTCOMES

After the course the student:

1. Will be able to recognize the basic terminology employed in the field of machine learning and AI: supervised vs unsupervised learning; regression vs classification models.
2. Will understand the fundamentals of data analysis and probability: prior and posterior probabilities, and the Bayesian interpretation of probability.
3. Will know the basic features of mainstream models and algorithms: kernel/Gaussian regression, artificial neural networks, random forests, clustering, dimensionality reduction, low-dimensional embedding/visualization, image recognition, large language models, etc.
4. Will get some hands-on experience using mainstream ML/AI Python libraries/packages, like Sklearn and Pytorch, applied to relevant examples in chemistry and materials science (e.g., detecting atomic patterns in atomic force microscopy images).
5. Will get hands-on supervised experience applying the learnt principles to solve a small project of their choice, e.g., searching for stable molecules/materials with machine learning potentials, extending a large language model to include a given set of literature items, cataloguing a set of micrographs or spectrographs, training a high-dimensional model from a database of experimental results, etc. This will equip the student with the practical tools to use AI/ML to solve problems in their industrial or academic job after the course.

Credits: 5

Schedule: 25.02.2025 - 27.05.2025

Teacher in charge (valid for whole curriculum period):

Teacher in charge (applies in this implementation): Miguel Caro Bayo

Contact information for the course (applies in this implementation):

CEFR level (valid for whole curriculum period):

Language of instruction and studies (applies in this implementation):

Teaching language: English. Languages of study attainment: English

CONTENT, ASSESSMENT AND WORKLOAD

Content

• valid for whole curriculum period:

  Valid for whole curriculum period:

  1. Fundamentals of machine learning and AI: theory and algorithms.
  2. Mainstream Python libraries for basic AI/machine learning tasks: regression, classification, pattern recognition.
  3. Contemporary use of machine learning and AI in chemical research (industry/academia) and production/processes (industry).
  4. Selected examples relevant to research in the Chemistry and Materials Science department, e.g., machine learning potentials for atomistic modeling.
  5. Selected seminars by invited academics and Finnish industry representatives.

Assessment Methods and Criteria

• valid for whole curriculum period:

  Valid for whole curriculum period:

  Weekly exercise assignments (50%, can miss two) and final project (50%).

Workload

• valid for whole curriculum period:

  Valid for whole curriculum period:

  • Lectures and invited seminars 24 h
  • Exercises and hands-on sessions 24 h
  • Assignments and final project 36 h
  • Other independent studying 36 h

DETAILS

Study Material

• valid for whole curriculum period:

  The course notes will be provided by the teacher in charge, covering the bulk of the lecture materials imparted in the course and with appropriate bibliographic references for further reading material.

  Exercises will be provided together with the notes and exercise solutions will be provided after the exercise assignments have been handed in by the students.

  Notes and other primarily text-based material will be provided via MyCourses.

  The materials for hands-on sessions and other practical codes, scripts, etc., will be provided by the teacher in charge, generally via Github or a similar centralized repository.

Substitutes for Courses

• valid for whole curriculum period:

  Substitutes for Courses

Prerequisites

• valid for whole curriculum period:

  Prerequisites

FURTHER INFORMATION

Further Information

• valid for whole curriculum period:

  Teaching Language: English

  Teaching Period: 2024-2025 Spring IV - V
  2025-2026 Spring IV - V

  Registration:

  A maximum of 25 students are accepted to the course. Priority will be given to students in the following order: 1) MSc students of the School of Chemical Engineering who have completed recommended prerequisite course(s); 2) MSc students of the School of Chemical Engineering without recommended prerequisite course(s); 3) other students.

  A course implementation may be cancelled if the number of students enrolled to the course implementation does not meet the required minimum of five students. In the case of cancelled course implementations, the students enrolled to them must be provided with an alternative way of completing the course or be advised to take some other applicable course.

Description