Machine learning researcher, postdoc. Investigating differentiable algorithms etc. @Stanford @StanfordAILab.
Bay Area
Joined November 2016
- Tweets171
- Following299
- Followers2.3K
- Likes708
Felix Petersen retweeted
The next generation of neural networks could live in hardware trib.al/65TrkHz
Felix Petersen retweeted
#UniKonstanz Informatiker Felix Petersen bekommt für seine Dissertation am Fachbereich Informatik und Informationswissenschaft den Förderpreis des Arbeitgeberverbandes Südwestmetall verliehen. t1p.de/jgwor @Suedwestmetall @mwk__bw
Felix Petersen retweeted
Paper accepted to #CVPR2024!
Grounding Everything: Emerging Localization Properties in Vision-Language Transformers
Paper: arxiv.org/abs/2312.00878
Demo:huggingface.co/spaces/WalidB…
Code: github.com/WalBouss/GEM
With @BousselhamWalid, @FHKPetersen, @HildeKuehne
Felix Petersen retweeted
Lawrence Stewart (INRIA) talking about perturbed optimizers for making clustering differentiable 🌴. Differentiable Almost Everything Workshop at ICML 2023. Room 310.
Felix Petersen retweeted
I am going to #ICML2023 in Honolulu 🌺 next week!
I will present some recent work with Marin Ballu (Cambridge).
I will also give an invited talk at the "Differentiable Almost Everything" workshop.
-More info on both below 🧵
Ping me if you want to connect there!
Felix Petersen retweeted
The preprint of our paper ''Neural Machine Translation for Mathematical Formulae'' is now up on GippLab.org
📰: gipplab.org/wp-content/paper…
It will be presented at #ACL2023NLP in Toronto 🇨🇦
@FHKPetersen @physikerwelt @GreinerPetter @BelaGipp
Felix Petersen retweeted
Happy to announce that our workshop on Differentiable Almost Everything #diffxyz got accepted to #ICML2023
Check out the website: differentiable.xyz/
@FHKPetersen @CuturiMarco @Mniepert @Michael_A_Kagan @willieneis @StefanoErmon
CfP coming soon!
Felix Petersen retweeted
Deep Differentiable Logic Gate Networks
ai.papers.bar/paper/9373842c…
logic gate networks are non-differentiable and do not allow gradient descent training. The architecture combines real-valued logics and a continuously...
🧵 👇
Felix Petersen retweeted
I found rather interesting «Deep Differentiable Logic Gate Networks» by @fhkpetersen. Learning combinational networks comprising logic gates such as AND and XOR, which allow for very fast execution and hardware implementation. #NeurIPS22
arxiv.org/abs/2210.08277
Felix Petersen retweeted
Learning with Differentiable Algorithms
If you’re interested in making algorithms differentiable so that algorithms can be learned from training data, @FHKPetersen’s thesis covers differentiable versions of Sorting and Ranking, Top-k, Rendering, Logic.
arxiv.org/abs/2209.00616
Felix Petersen retweeted
Our team at @IBMResearch is excited to announce inFairness - the first open-source Python library for Individual Fairness in AI.
GitHub: github.com/IBM/inFairness
Website: ibm.github.io/infairness
A 🧵on what the library offers and the functionalities implemented within it.
Felix Petersen retweeted
Video is available here: youtube.com/watch?v=J-lZV72D…
Feel free to drop by at #ICML2022 : Spotlight: Wed 1:25-1:30 p.m. EDT @ Ballroom 1 & 2
Poster: Wed 6:30-8:30 p.m. EDT @ Hall E #328
Felix Petersen retweeted
Happy to finally share our paper about differentiable Top-K Learning by Sorting that didn’t make it to #CVPR2022, but was accepted for #ICML2022! We show that you can improve classification by actually considering top-1 + runner-ups… 1/6🧵
#ComputerVision #AI #MachineLearning
