We live in interesting times!
A combination of post-Moore’s law era and the advent of very large ML models require all of us to think up new approaches to computing hardware and AI algorithms at the same time. LightOn is one of the few (20) companies in the world publishing in both AI and hardware venues to engage both communities into thinking how theories and workflows may eventually be transformed by the photonic technology we develop.
This year, thanks to the awesome Machine Learning team at LightOn, we have two accepted papers at NeurIPS, the AI flagship conference, and have five papers in its“Beyond Backpropagation” satellite workshop that will take place on Saturday. This is significant on many levels, not the least being that these papers have been nurtured and spearheaded by two Ph.D. students (Ruben Ohana and Julien Launay) who are doing their thesis as LightOn engineers.
Here is the list of the different papers accepted at NeurIPS this year that involved LightOn members:
Reservoir Computing meets Recurrent Kernels and Structured Transforms, Jonathan Dong, Ruben Ohana, Mushegh Rafayelyan, Florent Krzakala. Links: Oral, poster, paper (presenter: Ruben Ohana). Poster Session 4 on Wed, Dec 9th, 2020 @ 18:00–20:00 CET. GatherTown: Deep learning ( Town E1 — Spot C0 ) Join GatherTown. Only if and only if poster is crowded, join Zoom
Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures, Julien Launay, Iacopo Poli, François Boniface, Florent Krzakala. Links: Poster, paper (Presenter: Julien Launay). Poster Session 6, on Thu, Dec 10th, 2020 @ 18:00–20:00 CET. GatherTown: Neuroscience and Cognitive Science ( Town A3 — Spot B0 )
And at the NeurIPS Beyond Backpropagation workshop taking place on Saturday, December 12
- Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment, Julien Launay, Iacopo Poli, Kilian Muller, Igor Carron, Laurent Daudet, Florent Krzakala, Sylvain Gigan
- Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures, Julien Launay, François Boniface, Iacopo Poli, Florent Krzakala (Presenter: Julien Launay).
- Ignorance is Bliss: Adversarial Robustness by Design through Analog Computing and Synaptic Asymmetry, Alessandro Cappelli, Ruben Ohana, Julien Launay, Iacopo Poli, Florent Krzakala (Presenter: Alessandro Cappelli). We had a blog post on this recently.
- Align, then Select: Analysing the Learning Dynamics of Feedback Alignment, Maria Refinetti, Stéphane d’Ascoli, Ruben Ohana, Sebastian Goldt paper (Presenter: Ruben Ohana).
- How and When does Feedback Alignment Work, Stéphane d’Ascoli, Maria Refinetti, Ruben Ohana, Sebastian Goldt. paper (Presenter: Ruben Ohana)
Some of these presentations are given in French at the “Déjeuners virtuels de NeurIPS”