TIdDLe events
This is a list of "official" TIdDLe events. For a list of other Deep Learning related events, see our forum.Upcoming events
Second TIdDLe Seminar (June 24th, 2022)
After the long pause due to the COVID restrictions, we are very glad to finally have our second seminar! We will kick off with a double presentation from Bhavin Choksi and Milad Mozafari about their paper "Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics". The presentation will revolve around their latest work published last year at NeurIPS, about introducing brain-inspired dynamics in a deep network to improve their robustness to noise and adversarial attacks.
It will take place the 24th of June from at 16:00 on the 24 of June, in Salle des Thèses (C002) of INP-ENSEEIHT. The main entrance is located at 2 rue Charles Camichel (quarter Saint-Aubin). Visitors should press the bell/button "Accueil" and inform the welcoming desk of the purpose of the visit (attendance of the seminar). Room C002 is located in building C, ground-floor. Everybody is welcome to join! After the presentation, we will move the discussion to the closest bar for a deepBeer!
Past Events
Third DeepBeer (Jan 31st, 2020)
Next DeepBeer will take place next Friday the 31st of January, at the Le Pery from 18:30!
Don't hesitate to join us for a deeply chill time after a long Friday of work! We are looking forward to see you there!
KeyNote Lecture - Thomas Serre (ANITI / Brown University) (Jan 14th, 2020)
First keyNote conference took place on January the 14th, 2020 with Thomas Serre (ANITI/Brown University) as invited speaker.
Find the slides of the presentation here
Second DeepBeer (Dec 18th, 2019)
Second DeepBeer meeting will take place at the Bieregarten at 21:00.
As usual, everyone is welcome to join, so don't be shy and come have a chill time!
NeurIPS meetup (Dec 16th, 2019)
Did you want to go to NeurIPS but couldn't make it this year? No problem, we're here to help... Toulouse Data Science and TIdDLe are co-organizing a one-day NeurIPS meetup (officially approved by the NeurIPS organizers). The event will take place on December 16th, in the Auditorium of the Village By Ca (31 allées Jules Guesdes, close to Palais de Justice).
Registration is free and open to anyone, but the number of participants is limited. If you wanted to join but didn't register yet, you may still email andrea.alamia@cnrs.fr to make a request, we'll try our best to accommodate you. Similarly, if you registered but finally won't be able to come, please let us know so we can offer your spot to somebody else.
Here is the final program of the event :
| 09:30 - 10:00 | Welcome and Introduction |
|---|---|
| 10:00 - 10:15 | Projection 1: "Uniform convergence may be unable to explain generalization in deep learning" |
| 10:15 - 10:45 | "Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning" by Emmanuel Rachelson and Erwan Lecarpentier (ISAE/SUPAERO) |
| 10:45 - 11:00 | Projection 2: "Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs" |
| 11:00 - 11:30 | "Bio-inspired few-shot learning on the edge with Akida" by Sebastien Crouzet and Douglas McLelland (BrainChip) |
| 11:30 - 12:00 | "Neural Networks for Poetry and Song Generation" by Tim Van de Cruys (IRIT/ANITI) |
| 12:00 - 13:30 | Buffet lunch |
| 13:30 - 13:45 | Projection 3: "Causal Confusion in Imitation Learning" |
| 13:45 - 14:15 | "Training convolutional spiking neural networks with backpropagation through time & application to speech processing" by Thomas Pellegrini and Timothée Masquelier (IRIT, CerCo) |
| 14:15 - 14:30 | Projection 4: "Geometry-Aware Neural Rendering" |
| 14:30 - 15:00 | "3D trajectories analysis using spiking cameras" by Guillaume Debat, R. Baurès, B. Cottereau, T. Masquelier, T. Chauhan, C. Joly, O. Brousse, M. Paindavoine (CerCo) |
| 15:00 - 15:30 | Coffee break |
| 15:30 - 15:45 | Projection 5: "A neurally plausible model learns successor representations in partially observable environments" |
| 15:45 - 16:15 | "Asymptotically exact data augmentation: models, algorithms and theory" by Maxime Vono, Nicolas Dobigeon and Pierre Chainais (IRIT/ENSEEIHT) |
| 16:15 - 17:00 | Round table / General discussion |
| 17:00 - 18:00 | Cocktail |
Coffee breaks, buffet lunch and cocktail are graciously provided by ANITI!
All presentations (local and remote) will be in English. Anybody is welcome to join, so feel free to spread the word!
First TIdDLe Seminar (Dec 2nd, 2019)
The first seminar will take place the 2nd of December from 14:30 to 15:30 at the IRIT Auditorium in the Paul Sabatier Campus. We will have two speakers, and each presentation will last 20 minutes plus an additional 10 minutes for questions. Everybody is welcome to join!
The speakers are Bhavin Choksi from CerCo who will present his current work on biologically inspired neural networks, and Vincent Roger from IRIT who will provide an overview about few-shot learning techniques.
First DeepBeer (Nov 18th, 2019)
It was the right time to turn on our TIdDLe community! A good starter to get to know each other with a very informal event: our first DeepBeer meeting at Le Pery (https://www.lepery.com/).
The idea of the Deep Beer Meeting is to have a monthly event which gathers Tiddle members in front of a (few) beer(s). It's informal, fun and with variable location! The goal is to get to know each other without necessarily talking about Deep things. Everyone is welcome to join, so feel free to spread the invitation to friends and colleagues!
Inaugural meeting (Feb 7th, 2019)
Our inaugural meeting took place at the B612 "Aerospace Valley" building on February 7th, 2019.
About 80 permanent researchers from academia and industrial partners registered to the event.
We had plenty of general discussions, before, after and during the 16 scientific presentations.
Group organization issues were discussed, ideas for future events, and modes of operation (including
the present website and the list of members expertise with contact info).
The final cocktail was much appreciated, especially the apple cider.