Course 2023-2024 a.y.

20880 - MACHINE LEARNING LAB

Department of Computing Sciences

Course taught in English
Go to class group/s: 29
AI (2 credits - II sem. - OB  |  INF/01)
Course Director:
FRANCESCA BUFFA

Classes: 29 (II sem.)
Instructors:
Class 29: FRANCESCA BUFFA


Suggested background knowledge

For a fruitful and effective learning experience, it is recommended knowledge of basic linear algebra, elements of probability and statistics, calculus, optimization and programming (Python)

Mission & Content Summary

MISSION

The purpose of the lab will be to apply basic machine learning techniques to real data. Students will be expected to tackle fundamental problems in the life sciences and learn how to extract relevant information from complex data. The projects will be preceded by an introduction of the relevant domain knowledge needed to be able to critically evaluate the results obtained.

CONTENT SUMMARY

Introduction to the use of AI in the Life Sciences: Basics concepts, Open questions, Methods, Challenges

Lab work: the students will be asked to address an open question in the life sciences, and will be given access to a series of datasets to address this question. The student will learn how to explore the data, evaluate applicability and apply advanced ML methods, focusing on methods studied in the course associated with the lab, and write a final report discussing their choices and results.


Intended Learning Outcomes (ILO)

KNOWLEDGE AND UNDERSTANDING

At the end of the course student will be able to...
  • Handle complex databases
  • Apply different types of algorithms for unsupervised and supervised data analysis: from basic algorithms to deep models
  • Evaluate performance based on domain knowledge and rigorous tests.

APPLYING KNOWLEDGE AND UNDERSTANDING

At the end of the course student will be able to...
  • approach the solution to data analysis problems coming from a real world context,
  • use fundamental machine learning algorithms, including deep learning.
  • critically evaluate the results

Teaching methods

  • Face-to-face lectures
  • Group assignments
  • Interactive class activities on campus/online (role playing, business game, simulation, online forum, instant polls)

DETAILS

  • Lectures and exercises: Concepts in data analysis using machine learning and deep learning to extract infomation from datasets of real world interest. The necessary domain specific knowledge will be provided.
  • Group assignement: solve a real prediction problem
  • Presentation of project as a group

Assessment methods

  Continuous assessment Partial exams General exam
  • Written individual exam (traditional/online)
    x
  • Oral individual exam
    x
  • Individual assignment (report, exercise, presentation, project work etc.)
    x
  • Group assignment (report, exercise, presentation, project work etc.)
    x

ATTENDING AND NOT ATTENDING STUDENTS

The assesment will be based on the outcome of the group projects. A written report will be required for the group. The group members will have to give an oral presentation together at the exam session. Individual assessmet: each student will be asked to present and discuss their contribution to the project and the report. Grading scheme: Group project: 50% Individual assessment: 50%

 

 

 


Teaching materials


ATTENDING AND NOT ATTENDING STUDENTS

All data, instructions and study material will be provided during the course

Last change 06/02/2024 10:49