Matias Calderini

Data Scientist. Special love for good data visualization.

[Olivier Lizotte - explor.ai @ocltech]

Le cours monté par @expIorai est finalement en ligne! Première cohorte 22 novembre 2021: https://t.co/bK5wCWMPOJ

[Grid.ai @gridai_]

🎉Excited to share the latest paper from Grid AI Labs: A new approach to #SelfSupervisedLearning based on autoencoding (AAVAE), which achieves comparable results to contrastive methods while reducing training complexity.

Paper https://t.co/oqtvgtf4f4
Code https://t.co/8NbPTmfnE2

[Towards Data Science @TDataScience]

Mining customer opinions can be a powerful way to generate business insights. @VidushiBhatia shows how do it with Transformers. https://t.co/39pYMHPiY9

[Alex Nichol @unixpickle]

Now anybody can tinker with and explore the current SOTA generative image models! We have released model weights for our paper "Diffusion Models Beat GANs on Image Synthesis": https://t.co/bKW2OkgiLp

[Ali Madani @thisismadani]

This twirling work of science is special ✨

AFAIK, it's the first crystal structure of a functional #protein fully designed by #AI

A milestone in our quest to use language models to generate proteins that are unseen in nature & can function well in the real-world. Read below👇

[ICML Conference @icmlconf]

🧵We are pleased to announce the ICML 2021 paper awards. Congratulations to all authors!

Test of the Time Award from ICML 2011:
• Max Welling and Yee Whye Teh
📜Bayesian Learning via Stochastic Gradient Langevin Dynamics

[Demis Hassabis @demishassabis]

Last year we presented #AlphaFold v2 which predicts 3D structures of proteins down to atomic accuracy. Today we’re proud to share the methods in @Nature w/open source code. Excited to see the research this enables. More very soon!

https://t.co/6uiV51Xly5
https://t.co/CLo7EKubBT

[Adi Polak @AdiPolak]

Microsoft partnered with PyTorch to provide you with a completely FREE PyTorch fundamentals course.

The course includes a built-in sandbox experience where you can code directly from your browser.

No need to install/download anything, just schedule the time to learn.

Link ⤵️

[Towards Data Science @TDataScience]

Handle missing data like a pro and learn how to make the most of imputation methods — @TGIFrancis shows how. https://t.co/GwLlcSceqR

[Lightning AI ⚡️ @LightningAI]

⚡️📚 This tutorial shows how to improve model resource inference efficiency using #quantization with PyTorch Lightning.

In part two of this series, we introduce the fundamentals of optimizing models with quantization. https://t.co/7I5fkv24of

[James Briggs @jamescalam]

I just posted article #100 on @Medium with @TDataScience 🎉

And it's a big one! How to train BERT models from scratch, creating an Italian-speaking BERT - FiliBERTo 🇮🇹

https://t.co/dpQbFW8Gg5

[Matias Calderini @MatiCalderini]

@Pi_In_The_Sky @matplotlib I am biased but... I think my #matplotlib tutorials are quite good. I should have a pandas one coming out soon as well:

https://t.co/dnWLaL2pkU

https://t.co/VhLN5kON3w

Good luck!

[clem 🤗 @ClementDelangue]

Similarly to @Github copilot, you can now do question-answering in Google Sheet thanks to the TAPAS model from @GoogleAI & the @huggingface inference API.

Machine Learning making its way in each and every product! Great job @osanseviero!

[AK @_akhaliq]

Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
pdf: https://t.co/tx0OH7nkNg
abs: https://t.co/bZAuunEksJ
github: https://t.co/8awlEeSWOw

[Spain AI @Spain_AI_]

Agenda de Julio #AI 🔥🤖
📆Martes 6 - 19h
🗣️Hablamos de Algoritmos bioinspirados con 2 charlas magistrales y @Asturias_AI
📍Biología evolutiva en la #Robotica del Futuro con Patricia Llaque
📍Tecnología y #Economia Circular con @mgvazq
¡Reserva ya! 🎟️
https://t.co/QmwM4lv7Yd

[AK @_akhaliq]

Small in-distribution changes in 3D perspective and lighting fool both CNNs and Transformers
pdf: https://t.co/1zhF7xYao4

networks are brittle to both small 3D perspective changes and lighting variations which cannot be explained by dataset bias or lack of shift-invariance

[GitHub @github]

Meet GitHub Copilot - your AI pair programmer. https://t.co/eWPueAXTFt

[Csaba Kissi @csaba_kissi]

💡How to host your full-stack app for Free 👇

Front-end:
✅ Netlify
✅ Vercel
✅ Github pages

Back-end:
✅ Vercel (my preferred one)
✅ Netlify functions
✅ Google Cloud Functions

Database:
✅ Mongo Atlas
✅ Firebase
✅ FaunaDB

Add more 💬👇

[Fermat's Library @fermatslibrary]

This week's paper introduces the concept of Physics Informed Neural Networks - NN that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations

Paper: https://t.co/7rDWWuB5HY

[Microsoft Research @MSFTResearch]

Concurrent software is key to scaling to growing computing needs, but finding concurrency bugs is difficult. QL—an open-source RL-based controlled concurrency testing strategy—can expose bugs better than state-of-the-art human-designed CCT techniques: https://t.co/CQstVnOyNf