11th INTERNATIONAL SCHOOL ON DEEP LEARNING
(and the Future of Artificial Intelligence)
DeepLearn 2024
Porto =E2=80=93 Maia, Portugal
July 15-19, 2024
https://deeplearn.irdta.eu/2024/
******************************************************
Co-organized by:
University of Maia
Institute for Research Development, Training and Advice =E2=80=93 IRDTA
Brussels/London
******************************************************
Early registration: October 23, 2023
******************************************************
SCOPE:
DeepLearn 2024 will be a research training event with a global scope aiming=
at updating participants on the most recent advances in the critical and f=
ast developing area of deep learning. Previous events were held in Bilbao, =
Genova, Warsaw, Las Palmas de Gran Canaria, Guimar=C3=A3es, Las Palmas de G=
ran Canaria, Lule=C3=A5, Bournemouth, Bari and Las Palmas de Gran Canaria.
Deep learning is a branch of artificial intelligence covering a spectrum of=
current frontier research and industrial innovation that provides more eff=
icient algorithms to deal with large-scale data in a huge variety of enviro=
nments: computer vision, neurosciences, speech recognition, language proces=
sing, human-computer interaction, drug discovery, health informatics, medic=
al image analysis, recommender systems, advertising, fraud detection, robot=
ics, games, finance, biotechnology, physics experiments, biometrics, commun=
ications, climate sciences, geographic information systems, signal processi=
ng, genomics, materials design, video technology, social systems, etc. etc.
The field is also raising a number of relevant questions about robustness o=
f the algorithms, explainability and important ethical concerns at the fron=
tier of current knowledge that deserve careful multidisciplinary discussion=
.
Most deep learning subareas will be displayed, and main challenges identifi=
ed through 18 four-hour and a half courses, 2 keynote lectures, 1 round tab=
le and a few hackathon-type competitions among students, which will tackle =
the most active and promising topics. Renowned academics and industry pione=
ers will lecture and share their views with the audience. The organizers ar=
e convinced that outstanding speakers will attract the brightest and most m=
otivated students. Face to face interaction and networking will be main ing=
redients of the event. It will be also possible to fully participate in viv=
o remotely.
ADDRESSED TO:
Graduate students, postgraduate students and industry practitioners will be=
typical profiles of participants. However, there are no formal pre-requisi=
tes for attendance in terms of academic degrees, so people less or more adv=
anced in their career will be welcome as well.
Since there will be a variety of levels, specific knowledge background may =
be assumed for some of the courses.
Overall, DeepLearn 2024 is addressed to students, researchers and practitio=
ners who want to keep themselves updated about recent developments and futu=
re trends. All will surely find it fruitful to listen to and discuss with m=
ajor researchers, industry leaders and innovators.
VENUE:
DeepLearn 2024 will take place in Porto, the second largest city in Portuga=
l, recognized by UNESCO in 1996 as a World Heritage Site. The venue will be=
:
University of Maia
Avenida Carlos de Oliveira Campos - Cast=C3=AAlo da Maia
4475-690 Maia
Porto, Portugal
STRUCTURE:
3 courses will run in parallel during the whole event. Participants will be=
able to freely choose the courses they wish to attend as well as to move f=
rom one to another.
All lectures will be videorecorded. Participants will be able to watch them=
again for 45 days after the event.
An open session will give participants the opportunity to present their own=
work in progress in 5 minutes. Also companies will be able to present thei=
r technical developments for 10 minutes.
This year=E2=80=99s edition of the school will schedule hands-on activities=
including mini-hackathons, where participants will work in teams to tackle=
several machine learning challenges.
Full live online participation will be possible. The organizers highlight, =
however, the importance of face to face interaction and networking in this =
kind of research training event.
KEYNOTE SPEAKERS: (to be completed)
Jiawei Han (University of Illinois Urbana Champaign), How Can Large Languag=
e Models Contribute to Effective Text Mining?
PROFESSORS AND COURSES: (to be completed)
Luca Benini (Swiss Federal Institute of Technology Zurich), [intermediate/a=
dvanced] Open Hardware Platforms for Edge Machine Learning
Peng Cui (Tsinghua University), [intermediate/advanced] Stable Learning for=
Out-of-Distribution Generalization: Invariance, Causality and Heterogeneit=
y
Sergei V. Gleyzer (University of Alabama), [introductory/intermediate] Mach=
ine Learning Fundamentals and Their Applications to Very Large Scientific D=
ata: Rare Signal and Feature Extraction, End-to-End Deep Learning, Uncertai=
nty Estimation and Realtime Machine Learning Applications in Software and H=
ardware
Yulan He (King=E2=80=99s College London), [intermediate/advanced] Machine R=
eading Comprehension with Large Language Models
George Karypis (University of Minnesota), tba
Hermann Ney (RWTH Aachen University), tba
Massimiliano Pontil (Italian Institute of Technology), tba
Laurens van der Maaten (Meta AI), [introductory/intermediate] Introduction =
to Computer Vision
OPEN SESSION:
An open session will collect 5-minute voluntary presentations of work in pr=
ogress by participants.
They should submit a half-page abstract containing the title, authors, and =
summary of the research to david@irdta.eu by July 7, 2024.
INDUSTRIAL SESSION:
A session will be devoted to 10-minute demonstrations of practical applicat=
ions of deep learning in industry.
Companies interested in contributing are welcome to submit a 1-page abstrac=
t containing the program of the demonstration and the logistics needed. Peo=
ple in charge of the demonstration must register for the event.
Expressions of interest have to be submitted to david@irdta.eu by July 7, 2=
024.
HACKATHON ACTIVITIES:
A section of the event will consist of hands-on activities including mini-h=
ackathons, where participants will work in teams to tackle several machine =
learning challenges.
EMPLOYERS:
Organizations searching for personnel well skilled in deep learning will be=
provided a space for one-to-one contacts.
It is recommended to produce a 1-page .pdf leaflet with a brief description=
of the organization and the profiles looked for to be circulated among the=
participants prior to the event. People in charge of the search must regis=
ter for the event.
Expressions of interest have to be submitted to david@irdta.eu by July 7, 2=
024.
SPONSORS:
Companies/institutions/organizations willing to be sponsors of the event ca=
n download the sponsorship leaflet from
https://deeplearn.irdta.eu/2024/sponsoring/
ORGANIZING COMMITTEE:
Jos=C3=A9 Paulo Marques dos Santos (Maia, local chair)
Carlos Mart=C3=ADn-Vide (Tarragona, program chair)
Sara Morales (Brussels)
Jos=C3=A9 Lu=C3=ADs Reis (Maia)
Lu=C3=ADs Paulo Reis (Porto)
David Silva (London, organization chair)
REGISTRATION:
It has to be done at
https://deeplearn.irdta.eu/2024/registration/
The selection of 8 courses requested in the registration template is only t=
entative and non-binding. For logistical reasons, it will be helpful to hav=
e an estimation of the respective demand for each course.
Since the capacity of the venue is limited, registration requests will be p=
rocessed on a first come first served basis. The registration period will b=
e closed and the on-line registration tool disabled when the capacity of th=
e venue will have got exhausted. It is highly recommended to register prior=
to the event.
FEES:
Fees comprise access to all program activities and lunches.
There are several early registration deadlines. Fees depend on the registra=
tion deadline.
The fees for on site and for online participation are the same.
ACCOMMODATION:
Accommodation suggestions will be available at
https://deeplearn.irdta.eu/2024/accommodation/
CERTIFICATE:
A certificate of successful participation in the event will be delivered in=
dicating the number of hours of lectures. This should be sufficient for tho=
se participants who plan to request ECTS recognition from their home univer=
sity.
QUESTIONS AND FURTHER INFORMATION:
ACKNOWLEDGMENTS:
Universidade da Maia
Universidade do Porto
Universitat Rovira i Virgili
Institute for Research Development, Training and Advice =E2=80=93 IRDTA, Br=
ussels/London
**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************
Posts
