Advanced Applied Data Analytics 2026

Advanced Applied Data Analytics - January 2026

This course is the second, more advanced part of the diiP course “Applied Data Analytics.” The first part covers basic techniques, methodologies, and practical skills for data analysis. The second part delves into more advanced topics in Machine Learning and Deep Learning (see schedule below).

Like the first part, this course is intended for a variety of doctoral students from several faculties at Université Paris Cité. Key topics include data science, data analysis, machine learning, deep learning, and data mining.

Format of Lectures

This intensive course runs over one week in the winter, from Monday to Friday, between 10:00 AM and 1:00 PM, totalling approximately 15 hours.

Instruction includes slides, hands-on Google Colaboratory exercises, and questionnaires.

The course is conducted via Zoom.

Information

The last session took place from January 12-16, 2026. The next session will be held in January 2027.

Interested students can enrol through https://u-paris.fr/doctorat/advanced-applied-data-analytics/.

Enrolled students who need access to course materials should contact me via email.

Learning Outcomes

By the end of this course, students will:

• Understand the fundamentals of data-driven learning, including key AI and ML concepts.

• Gain familiarity with transformer architectures, their applications in sequence modelling, and how they power modern AI models.

• Develop an in-depth understanding of Graph Neural Networks (GNNs) and their use in processing structured data

• Learn about Self-Supervised Learning, including its role in training AI models without labelled data.

• Explore Generative Adversarial Networks (GANs) and how they are used in data synthesis and augmentation.

• Master Probabilistic Modelling and Bayesian approaches for uncertainty estimation in machine learning models.

• Understand the applications of probabilistic techniques in data analytics, decision-making, and predictive modelling.

Instruction Methods

• Lectures via Zoom using slides

• Practical exercises with Google Colaboratory

• Interactive polls and Q&A sessions

Assessment

• Participation in class, discussions and polls

Course Material

The Zoom codes to view the recordings are available in the Introduction Lecture.
Students who need access to course materials should please email me.

Zoom Link

Here is the Zoom link to follow the lectures live.
You will also find the passwords required to access the recorded lectures.

Folder for the presentations by the students

Lecture 1 & 2 - Introduction, Generative Models: GANs and Autoencoders
Zoom Recording 1
Colaboratory Notebooks

GANs:

• Generative Adversarial Networks (GANs) on MNIST dataset

• Image-to-Image Translation with CycleGAN

• WGAN-Based Photomultiplier Pulse Refinement

Autoencoders:

• Dynamic Masked Autoencoder with Linear Layers

• Dynamic Masked Autoencoder with CNN

• Autoencoder on MNIST dataset: Image Reconstruction & Latent Space Analysis

• Autoencoder on MNIST dataset: Denoising images for Digit Restoration

Lecture 3 - Transformers and Pre-Trained Models
Zoom Recording 2
Colaboratory Notebooks

Pre-Trained Models:

• Zero-shot and fine-tuning of DINOv2 with an image dataset for clustering

• Time-series analysis with MOMENT

• Tabular Data Analysis with TabPFN

Lecture 4: Graph Neural Networks

Zoom Recording 3
Colaboratory Notebooks:

• Graph-Level Classification with a GNN

• Paper Type Prediction with a GNN

Lecture 5: Probabilistic Learning
Zoom Recording 3
Colaboratory Notebooks

• Exploring Bayesian Regression for Uncertainty Quantification in Predictions

• VAE on MNIST: Learning and Visualizing a Probabilistic Latent Space

Lecture 6: Hyperparameter Tuning

Zoom Recording 4

Colaboratory Notebooks:

• Random Search Parameter Tuning

• Optuna Bayesian Optimization

• Parameter Tuning Visualization with TensorBoard

Lecture 7: Dimensionality Reduction

Colaboratory Notebooks:

• PCA, t-SNE, UMAP

• Clustering after Dimensionality Reduction

• UMAP Inverse transform

Lecture 8: Knowledge-Informed Neural Networks
Zoom Recording 5
Colaboratory Notebooks

• Knowledge-informed NN (PINN-style): data loss + physics loss with PyTorch

• JAX Knowledge-informed NN (PINN-style): data loss + physics loss

• (JAX/Flax): Deterministic NN + BNN

Daily Attendance Polls

Monday Poll

Tuesday Poll

Wednesday Poll

Thursday Poll

Friday Poll