Teaching plan for the course unit

 

 

Close imatge de maquetació

 

Print

 

General information

 

Course unit name: Intel·ligència Artificial

Course unit code: 366702

Academic year: 2021-2022

Coordinator: Roser Sala Llonch

Department: Department of Biomedical Sciences

Credits: 4,5

Single program: S

 

 

Estimated learning time

Total number of hours 112.5

 

Face-to-face and/or online activities

54

 

-  Lecture

Face-to-face and online

 

24

 

-  Laboratory session

Face-to-face

 

14

 

-  Special practices

Face-to-face

 

6

 

-  Seminar

Face-to-face

 

10

Supervised project

16

Independent learning

42.5

 

 

Competences to be gained during study

 

   -

To be able to resolve problems with initiative and creativity and to take technological decisions in accordance with criteria of cost, quality, safety, sustainability, time and respect for the profession's ethical principles (Instrumental).

   -

To be able to analyse and summarize (Instrumental).

   -

To be able to work in a team or a multidisciplinary group (Personal).

   -

To be able to work in a multilingual environment and communicate and transmit knowledge, procedures, results, abilities and skills (oral and written) in a native and a foreign language (Instrumental).

   -

To gain knowledge of biomedical concepts and language.

   -

To use systems for the search and retrieval of biomedical information and procedures for clinical data. To be able to understand and critically interpret scientific texts and their sources.

   -

To know the basic aspects of descriptive and inferential statistical methods and to be able to use these in the biomedical sciences.

   -

To be able to conceive, design and produce equipment and systems, especially those for biology and medicine. In particular, to be able to incorporate algorithms for processing information into the appropriate hardware.

   -

As far as possible, the gender perspective will be incorporated throughout the development of the course.

 

 

Learning objectives

 

Referring to knowledge

To understand the basis of artificial intelligence, including an historical view and its main branches

 

To understand the nature of data in the clinical and biomedical fields.

 

To know the basic methods in machine learning.

 

To learn the basic methods in deep learning.

 

To be able to design and implement an AI-based application given a question to be solved and a dataset.

 

To know the techniques of transcriptomics, proteomics and metabolomics. 

 

To know the methods of standardization and data integration

 

Referring to abilities, skills

To know the problems related to data inhomogeneity and inaccurate labeling, and to be able to design solutions to overcome these problems.

 

To be able to discuss the results and their applicability knowing the limitations of the methods as well as the characteristics of the data in the biomedical engineering field.

 

To be able to program the main machine learning algorithms.

 

To be able to evaluate the performance of the methods by obtaining quantitative metrics.

 

To be able to analyse multidimensional data.

 

To know, and to know how to apply the methods for analysis and modelling of complex biological networks.

 

Referring to attitudes, values and norms

To be able to evaluate the ethical impact of artificial intelligence in biomedical engineering. 

 

 

Teaching blocks

 

1. Introduction to Artificial Intelligence in Biomedical Engineering

1.1. Machine Learning and Deep Learning

1.2. Discriminability vs interpretability

1.3. The nature of biomedical data: Data modelling and representation

1.4. Transcriptomics, proteomics and metabolomics

1.5. Feature extraction

2. Main Algorithms in Machine Learning

2.1. KNN and other basic classification algorithms

2.2. SVM and other linear classifiers

2.3. Non-linear classifiers

2.4. Clustering algorithms

2.5. Trainning and validation

3. Deep Learning

3.1. Basic concepts in deep learning.

3.2. Main deep learning algorithms

4. Databases and applications in Biomedical Engineering

4.1. Data acquisition and preprocessing

4.2. Feature selection techniques 

4.3. Data curation methods 

5. Seminars: Applications of AI in Biomedical Engineering

*  Series of seminars in which biomedical experts will explain different applications of artificial intelligence. The students will participate actively in the seminars.

6. Practical sessions

*  Hands-on exercises on specific methods

7. Project

*  Development of a full AI project using real data

 

 

Teaching methods and general organization

 

The course will be organised into: class lectures, seminars, practical sessions, and project development sessions.

The lectures will provide the theoretical basis of the main algorithms and definitions. 

The seminars will consist on class activities to see different applications of AI in the biomedical and clinical setting. 

The practical sessions will consist on short guided exercises focused on single aspects of the course. These sessions will be designed as hands-on tutorials using different programming languages (R/python/matlab).   

Throughout the semester, students will develop a project in groups of 4-5. Each group will work on a different dataset and a different problem, supervised by one of the professors of the course. 

The course will be taught completely in English. 

 

 

Official assessment of learning outcomes

 

The course grade will be a weighted average of the different activities performed during the semester. It will be calculated as follows: 

  • Continuous assessment (30%): Practical sessions and other activities during the course. 
  • Project (30%):  presentation of written report and validation of the code. 
  • Final exam (40%): written assessment of theoretical and practical aspects of the course. 


In order to pass the subject, students must achieve a grade of at least 5/10 of the total and a grade of at least 4/10 in the final exam. 

Repeat assessment: Students who fail to pass the subject can repeat assessment. To be eligible to repeat assessment, students must abide by the Academic Committee’s regulations for the bachelor’s degree. Students who have sit the first assessment procedure and fail to pass can repeat assessment of the final examination. Practical sessions cannot be repeated.

Exam revision: The exam revision system follows the UB regulations for assessment and grading of learning outcomes.

 

Examination-based assessment

Students can request single assessment and waive their right to continuous assessment before the established deadline.

The course grade will be a weighted average of the different activities performed during the semester. It will be calculated as follows: 

  • Project (30%):  presentation of written report and validation of the code. 
  • Final exam (70%): written assessment of theoretical and practical aspects of the course. 


In order to pass the subject, students must achieve a grade of at least 5/10 of the total and a grade of at least 4/10 in the final exam. 

Repeat assessment: Students who fail to pass the subject can repeat assessment. To be eligible to repeat assessment, students must abide by the Academic Committee’s regulations for the bachelor’s degree. Students who have sit the first assessment procedure and fail to pass can repeat assessment of the final examination. Practical sessions cannot be repeated.

Exam revision: The exam revision system follows the UB regulations for assessment and grading of learning outcomes.