diiP Summer School 2024 - dSDS
de
lundi 10 juin 2024 (08:00)
à
vendredi 14 juin 2024 (18:30)
lundi 10 juin 2024
08:00
Travel to venue
Travel to venue
08:00 - 13:00
Room: 418C, Halle aux Farines
13:00
Lunch
Lunch
13:00 - 14:30
Room: 712B-Cafétéria_7ème
14:30
AI for Research
-
Themis Palpanas
(
LIPADE - Paris Descartes University
)
Yvonne Becherini
(
Université Paris Cité
)
AI for Research
Themis Palpanas
(
LIPADE - Paris Descartes University
)
Yvonne Becherini
(
Université Paris Cité
)
14:30 - 16:00
Room: 418C, Halle aux Farines
16:00
Coffee break
Coffee break
16:00 - 16:30
Room: 418C
16:30
Large Language Models (LLMs)
-
Benoît Crabbé
(
Université Paris Cité
)
Large Language Models (LLMs)
Benoît Crabbé
(
Université Paris Cité
)
16:30 - 18:00
Room: 418C, Halle aux Farines
Large language models have become ubiquitous. This lecture introduces to language modelling and large language models. We will discover what they are, where they come from and the primary motivations behind their design. We then provide an overview of the properties of these models when trained at the current scale of very large language models. If time remains, we introduce the problematic of explaining their behaviour.
18:00
Networking/Free time
Networking/Free time
18:00 - 18:30
Room: 418C, Halle aux Farines
19:00
Social Dinner - Bouillon Racine
Social Dinner - Bouillon Racine
19:00 - 21:00
Room: Bouillon Racine
mardi 11 juin 2024
09:00
Supervised Learning
-
Alexandros Iosifidis
(
Aarhus University
)
Supervised Learning
Alexandros Iosifidis
(
Aarhus University
)
09:00 - 10:30
Room: 418C, Halle aux Farines
10:30
Coffee break
Coffee break
10:30 - 11:00
Room: 418C
11:00
Supervised Learning, Hands-on session
-
Alexandros Iosifidis
(
Aarhus University
)
Supervised Learning, Hands-on session
Alexandros Iosifidis
(
Aarhus University
)
11:00 - 12:00
Room: 418C, Halle aux Farines
12:00
AI in Medicine/Biology
-
Guillaume Assié
(
Institut Cochin, Inserm CNRS Université de Paris Cité
)
AI in Medicine/Biology
Guillaume Assié
(
Institut Cochin, Inserm CNRS Université de Paris Cité
)
12:00 - 13:00
Room: 418C, Halle aux Farines
13:00
Lunch
Lunch
13:00 - 14:30
Room: 712B-Cafétéria_7ème
14:30
Representation Learning
-
Jenni Raitoharju
(
University of Jyväskylä
)
Representation Learning
Jenni Raitoharju
(
University of Jyväskylä
)
14:30 - 16:00
Room: 418C, Halle aux Farines
16:00
Coffee break
Coffee break
16:00 - 16:30
Room: 418C, Halle aux Farines
16:30
Representation Learning - Hands-on session
-
Jenni Raitoharju
(
University of Jyväskylä
)
Representation Learning - Hands-on session
Jenni Raitoharju
(
University of Jyväskylä
)
16:30 - 17:30
Room: 418C, Halle aux Farines
17:30
Networking/Free time
Networking/Free time
17:30 - 20:00
Room: 418C, Halle aux Farines
mercredi 12 juin 2024
09:00
Knowledge-guided Data Science
-
Shen Liang
Knowledge-guided Data Science
Shen Liang
09:00 - 10:30
Room: 418C, Halle aux Farines
This lecture presents an overview of knowledge-guided data science, a rising methodology in machine learning which fuses data with domain knowledge. We will present numerous case studies on this methodology to showcase how to unleash its potential in real-world data science applications.
10:30
Coffee break
Coffee break
10:30 - 11:00
Room: 418C, Halle aux Farines
11:00
Knowledge-guided Data Science - Hands-on session (Basic)
-
Shen Liang
Knowledge-guided Data Science - Hands-on session (Basic)
Shen Liang
11:00 - 13:00
Room: 418C, Halle aux Farines
13:00
Lunch
Lunch
13:00 - 14:30
Room: 712B-Cafétéria_7ème
14:30
High-Dimensional Vector Similarity Search
-
Themis Palpanas
(
LIPADE - Paris Descartes University
)
High-Dimensional Vector Similarity Search
Themis Palpanas
(
LIPADE - Paris Descartes University
)
14:30 - 16:00
Room: 418C, Halle aux Farines
Very large amounts of high-dimensional data are now omnipresent (ranging from traditional multidimensional data to time series and deep embeddings), and the performance requirements (i.e., response-time and accuracy) of a variety of applications that need to process and analyze these data have become very stringent and demanding. In the past years, high-dimensional similarity search has been studied in its many flavors. Similarity search algorithms for exact and approximate, one-off and progressive query answering. Approximate algorithms with and without (deterministic or probabilistic) quality guarantees. Solutions for on-disk and in-memory data, static and streaming data. Approaches based on multidimensional space-partitioning and metric trees, random projections and locality-sensitive hashing (LSH), product quantization (PQ) and inverted files, k-nearest neighbor graphs and optimized linear scans. Surprisingly, the work on data-series (or time-series) similarity search has recently been shown to achieve the state-of-the-art performance for several variations of the problem, on both time-series and general high-dimensional vector data. In this talk, we will touch upon the different aspects of this interesting story, and present some of the state-of-the-art solutions.
16:00
Networking/Free time
Networking/Free time
16:00 - 18:00
Room: 418C, Halle aux Farines
19:15
Seine River Cruise and Social Dinner
Seine River Cruise and Social Dinner
19:15 - 22:45
Room: Bateaux-Mouches
jeudi 13 juin 2024
09:00
An Overview of Anomaly Detection for Time Series
-
Paul Boniol
(
INRIA & ENS
)
An Overview of Anomaly Detection for Time Series
Paul Boniol
(
INRIA & ENS
)
09:00 - 10:30
Room: 418C, Halle aux Farines
Anomaly detection is an important problem in data analytics with applications in many domains. In recent years, there has been an increasing interest in anomaly detection tasks applied to time series. In this talk, we take a holistic view of anomaly detection in time series, starting from the core definitions and taxonomies related to time series and anomaly types, to an extensive description of the anomaly detection methods proposed by different communities in the literature. We will then present new benchmarks capturing diverse domains and applications for the purpose of evaluating anomaly detection methods. We will then conclude on Ensembling and Model Selection for time series anomaly detection, discussing different strategies applicable to automatically selecting the appropriate methods for a specific time series.
10:30
Coffee break
Coffee break
10:30 - 11:00
Room: 418C, Halle aux Farines
11:00
Time Series Anomaly Detection in Practice - Hands-on session
-
Paul Boniol
Time Series Anomaly Detection in Practice - Hands-on session
Paul Boniol
11:00 - 12:00
Room: 418C, Halle aux Farines
12:00
AI in Industry
-
Paul Poncet
(
Engie
)
AI in Industry
Paul Poncet
(
Engie
)
12:00 - 13:00
Room: 418C, Halle aux Farines
13:00
Lunch
Lunch
13:00 - 14:30
Room: 712B-Cafétéria_7ème
14:30
Graph Neural Networks
-
Michalis Vazirgiannis
Graph Neural Networks
Michalis Vazirgiannis
14:30 - 16:00
Room: 418C, Halle aux Farines
16:00
Coffee break
Coffee break
16:00 - 16:30
Room: 418C, Halle aux Farines
16:30
Graph Generative AI + Applications
-
Michalis Vazirgiannis
(
École polytechnique, Palaiseau
)
Graph Generative AI + Applications
Michalis Vazirgiannis
(
École polytechnique, Palaiseau
)
16:30 - 18:00
Room: 418C, Halle aux Farines
18:00
Networking/Free time
Networking/Free time
18:00 - 20:00
Room: 418C, Halle aux Farines
vendredi 14 juin 2024
09:00
Generative adversarial networks and Active Learning
-
Amal Saadallah
(
TU Dortmund University
)
Generative adversarial networks and Active Learning
Amal Saadallah
(
TU Dortmund University
)
09:00 - 10:30
Room: 418C, Halle aux Farines
10:30
Coffee break
Coffee break
10:30 - 11:00
Room: 418C, Halle aux Farines
11:00
Generative adversarial networks and Active Learning - Hands-on session
-
Amal Saadallah
(
TU Dortmund University
)
Generative adversarial networks and Active Learning - Hands-on session
Amal Saadallah
(
TU Dortmund University
)
11:00 - 12:00
Room: 418C, Halle aux Farines
12:00
AI in Particle Physics
-
Yann Coadou
(
CPPM, Aix-Marseille Université, CNRS/IN2P3
)
AI in Particle Physics
Yann Coadou
(
CPPM, Aix-Marseille Université, CNRS/IN2P3
)
12:00 - 13:00
Room: 418C, Halle aux Farines
Particle physics deals with gigantic machines, large quantities of experimental data and computer simulations, complex and lengthy theoretical calculations. It is the perfect playground to take advantage of machine learning algorithms. After a short introduction to high energy physics, this lecture will show how one can speed up steps like event generation or detector simulation, better measure parameters, improve classification of events as signal or background, or discover anomalies in data taking, through various applications of machine learning in this field.
13:00
Lunch
Lunch
13:00 - 14:30
Room: 712B-Cafétéria_7ème
14:30
End of the diiP School
End of the diiP School
14:30 - 14:31
Room: 418C, Halle aux Farines