SachaIZADI

ML Engineer

[scikit-learn @ La Fondation Inria @sklearn_inria]

.@BCG joins the Consortium for another year as a Platinum Sponsor. We are grateful and happy to continue this exciting adventure together by supporting @scikit_learn. Thanks!

[SachaIZADI @sachaizadi]

@raphaelmeudec @PyTorch @TensorFlow Seems like there are other options: https://t.co/OTe3F0pV84 -- not sure which one works
best though

[SachaIZADI @sachaizadi]

.🆕

[TechCrunch @TechCrunch]

Google brings its ‘.new’ domains to the rest of the web, including to Spotify, Microsoft & others https://t.co/34nYUFYxgJ by @sarahintampa

[SachaIZADI @sachaizadi]

@iamtrask @seb_ruder Science

[vicki @vboykis]

Sorting Hat: Merge sort.
Harry Potter: Er, excuse me?
Sorting Hat: The white board, do a merge sort.
Harry Potter: But I thought Hogwarts was a mag-
Dumbledore: My dear boy, castle rent is much too expensive. We've pivoted to SaaS products. The hat does our interviews now.

[Andrej Karpathy @karpathy]

New blog post: "A Recipe for Training Neural Networks" https://t.co/5lBy4J77aS a collection of attempted advice for training neural nets with a focus on how to structure that process over time

[SachaIZADI @sachaizadi]

Useful checklist for debugging neural networks on https://t.co/Axw9qU4fgX

[Lex @TheLexTimes]

SF typical career path:

18: Go to Harvard or Stanford for CS.

22: Work at FAANG companies.

25: Quit and raise millions for your startup.

26: Sell your company to a FAANG company.

28: Join a VC firm, invest in people like you, and make predictions on Twitter all day.

[SachaIZADI @sachaizadi]

"You created a machine learning application. Now make sure it’s secure."
https://t.co/dIaVE5za4L

[SachaIZADI @sachaizadi]

😁

[Mario Klingemann💧💦 @quasimondo]

Latent Lisa, found in #StyleGAN #FindingMona

[SachaIZADI @sachaizadi]

@ColorizeImages @AlexandreMomeni

[Yann LeCun @ylecun]

Deep learning needs more theory.

Many workshops I have helped organize in the last decade (e.g. at IPAM) have attempted to bring ML/DL folks together with mathematicians and... https://t.co/jvOH36lYH8

[SachaIZADI @sachaizadi]

😵

[Auren Hoffman @auren]

deeper thoughts on how Amazon could leverage its AWS to dominate venture lending (and ultimately venture capital).

Amazon could up-end and dominate venture capital and venture lending https://t.co/aXUX1uYeoi

[Feross @feross]

Detect pressed keys via microphone audio capture in real-time. Uses training data captured by typing first. Very neat!

https://t.co/fIVbftye7D

Based on ideas in this classic traffic analysis paper: Timing Analysis of Keystrokes and Timing Attacks on SSH https://t.co/9r3gLRZIDg

[Mat Velloso @matvelloso]

Difference between machine learning and AI:

If it is written in Python, it's probably machine learning

If it is written in PowerPoint, it's probably AI

[Yann LeCun @ylecun]

Un documentaire sur l'IA diffusé sur Arte hier soir, où je suis filmé sous tous les angles dans mon environnement naturel. https://t.co/mK1uJCDuty

[Reza Zadeh @Reza_Zadeh]

What has been known empirically for a long time has been proven mathematically: Neural Networks can always fit to zero training error using gradient descent. Still open: proving why they generalize despite this insane overfitting capacity. https://t.co/pkvzNMH7hX

[C4 Ventures @c4ventures]

Today, @formlabs announced they joined the very small circle of #hardware Unicorns!! Well Done @MaxLobovsky and welcome @NEA https://t.co/e0zExscgR7 #HappyInvestor

[École polytechnique @Polytechnique]

Et si on réfléchissait à des solutions pertinentes pour un monde plus responsable ? C'est la thématique du prochain TedX, organisé par les élèves et intitulé Terre@terre. Rendez-vous le 2 mai prochain à l'X : https://t.co/HlbUKujzlr