philipp

[Max van Spengler @MvanSpengler]

Excited to introduce HypLL, our brand-new hyperbolic learning library developed together with @phippli and @PascalMettes!

1/4

[Igor Susmelj @ISusmelj]

Two years ago we released our open source framework for self supervised learning https://t.co/ppNFaaXIDB.
Today it's used by leading tech companies and research institutions all over the world, reached almost 2k GitHub stars and has been installed over 100k times.

[Igor Susmelj @ISusmelj]

We added support for the Masked Siamese Network (MSN) to @lightly. MSN learns image representations by comparing cluster assignments of masked and unmasked image views.
Great work by @mcaron31 @p_bojanowski @imisra_ @armandjoulin

https://t.co/xZq8AyadYl
https://t.co/ppNFaaXIDB

[Oliver Faude @OliverFaude]

Finally published @MSSEonline
👇
We developed and evaluated a deep learning approach to automatically segment anatomical cross-sectional area in panoramic ultrasound images of lower limb muscles.
🙏 @ritpau @MVFranchi @FabioSarto3 @NeilJCronin84 @phippli
https://t.co/uNkqoDlgtK

[Igor Susmelj @ISusmelj]

A friend just shared this with me. A great example for how deep learning models struggle with out-of-distribution data.
I wonder how many carriages the model has seen during training 😅

[Martino V. Franchi @MVFranchi]

Open access code & GUI ✅ +
Instructional video 📹:
https://t.co/yZd0eQKPMH
👌🏼⤵️

[Jerome Pesenti @an_open_mind]

Open source, @PyTorch, @PyTorchLightnin, self-supervision, and models from @facebookai and other labs, these are a few of my favorite things... Good luck Lightly! https://t.co/MhCePykGDP

[Igor Susmelj @ISusmelj]

Collaboration with @Arm: Embedded covid mask detection on an Arm Cortex-M7 processor using @PyTorch. From self-supervised pre-training to transfer learning, conversion to TensorFlow Lite, quantization, and running it on the device. All summarized here:
https://t.co/5RS3QyRZDY

[philipp @phippli]

@sidml12 @rasbt Thank you for your input! It's on my todo list - I will let you know when the update is ready :)

[philipp @phippli]

Thanks so much for sharing my blog post!

[Sebastian Raschka @rasbt]

"Which Optimizer should I use for my Machine Learning Project?" https://t.co/ea3d92diud

That's a neat quick reference table (personally, I am lazy and usually just stick to ADAM with default settings, works pretty well out of the box most of the time):