La version que vous consultez n'est pas définitive.
Cette fiche d’activité peut encore faire l'objet de modifications. La version finale sera disponible le 1er juin.
3.00 crédits
30.0 h + 10.0 h
Q1
Langue
d'enseignement
d'enseignement
Préalables
Master in Biomedical Sciences, Neurosciences or equivalent background (Exact Sciences, Psychology, Applied Sciences).
Thèmes abordés
1. AI Foundations and Data Handling
2. Preprocessing of data
3. Algorithms
4. Model Interpretability and Trustworthy AI
2. Preprocessing of data
3. Algorithms
4. Model Interpretability and Trustworthy AI
Acquis
d'apprentissage
d'apprentissage
A la fin de cette unité d’enseignement, l’étudiant est capable de : | |
| 1 | Explain different approaches in AI. |
| 2 | Students should be able to apply tools of AI on real biomedical data in a comprehensive manner. |
| 3 | Use a publicly available dataset (e.g., from Kaggle or TCGA) to build a classifier (e.g., predicting cancer subtype from gene expression data) in ‘R’ (keras & tensorflow R packages). |
Contenu
1. AI Foundations and Data Handling
- Introduction to AI in Biomedicine.
- Define AI, Machine Learning (ML), and Deep Learning (DL). Contrast traditional biostatistics with ML approaches.
- Learn how to clean, structure, and prepare diverse biomedical data for modeling.
- Data Types.
- Handling Missing Data and Data Imbalance
- Supervised Learning
- Unsupervised & Reinforcement Learning
- Convolutional Neural Networks (CNNs)
Méthodes d'enseignement
Ex-cathedra lessons, remotely if necessary. Group discussions. Computer exercises.
Modes d'évaluation
des acquis des étudiants
des acquis des étudiants
Oral or written examination (questions with written development or multiple choices).
Computer tests.
Computer tests.
Autres infos
Lectures will be given in English. Additional explanations will be provided in French if necessary.
Ressources
en ligne
en ligne
- Moodle
- https://r4ds.hadley.nz/
Faculté ou entité
en charge
en charge
