Daniel

[Khairallah AL-Awady @eng_khairallah1]

🚨 Anthropic just showed a 25-minute workshop on how to actually use Claude properly

Taught by the people who built it

Free. No registration. No paywall

I've seen $300 courses that don't cover what they teach in the first 8 minutes

Watch it and bookmark it now

[Aurélien Geron @aureliengeron]

Einops simplifies and clarifies array/tensor manipulation. 👍
You really have to try it out, you'll love it: https://t.co/XzbSunPj4S
Plus it supports NumPy, TensorFlow, PyTorch, and more.

[Andrej Karpathy @karpathy]

good quick tutorial on optimizing your PyTorch code ⏲️: https://t.co/7CIDWfrI0J
quick summary:

[Andrej Karpathy @karpathy]

Added a new demo to minGPT that trains a GPT on pixels of CIFAR-10 images instead of text. Quite powerful that one can run the same training code/model on both domains. Notebook: https://t.co/nAt9VWXnrG . Produced reasonable samples after ~only 30 minutes on an 8-GPU V100 node:

[Andrej Karpathy @karpathy]

I wrote a minimal/educational GPT training library in PyTorch, am calling it minGPT as it is only around ~300 lines of code: https://t.co/79S9lShJRN +demos for addition and character-level language model. (quick weekend project, may contain sharp edges)

[Jerome Pesenti @an_open_mind]

An in depth @FastCompany article with @schrep and @ylecun about @facebookai’s progress using self supervised learning to identify hate speech https://t.co/e0Cfoa2DJl

[Google DeepMind @GoogleDeepMind]

Gated Linear Networks (GLNs) are backpropagation-free neural nets designed for efficient online learning via local convex optimisation. We show their performance, interpretability & robustness to catastrophic forgetting on classification tasks - read here: https://t.co/8NTNDkXZDT

[Ian Ozsvald @[email protected] @ianozsvald]

Super happy to receive my author copy of 2nd ed of my High Performance Python, blog post with details will follow. Now available online/print. Please RT :-) Inc Pandas, GPUs, more profiling, async and more

[Banco Central BR @BancoCentralBR]

Muitos produtos vão nascer nesse ambiente novo, de inovação e competição. Saiba mais: https://t.co/kiPx9rgPDY

[DeepLearning.AI @DeepLearningAI]

Batch normalization is a technique that normalizes layer outputs to accelerate neural network training. But new research shows it has other important effects too. Its trainable parameters alone can account for much of a network's accuracy: https://t.co/ufE5vpbf9z

[Aurélien Geron @aureliengeron]

I wrote a Matplotlib tutorial notebook:
https://t.co/v9H3peLDmh
You'll learn how to make beautiful plots and animations, including, most importantly, XKCD-style plots:

[Aurélien Geron @aureliengeron]

I wrote a Colab notebook that introduces differential calculus: derivatives, partial derivatives and gradients: https://t.co/A2KAmux3B3

[Alex Kalinin @alxndrkalinin]

iResNet: Improved Residual Networks for Image and Video Recognition in #PyTorch
- improving ResNet performance w/o increasing parameters & computation
- more effective in training very deep models: >400 layers (on ImageNet) & >3000 layers (on CIFAR-10/100)
https://t.co/mFqHKFUGcZ

[PyTorch @PyTorch]

Captum is a library for model interpretability. Its algorithms include integrated gradients, conductance, SmoothGrad and VarGrad, and DeepLift. Learn more: https://t.co/IVdye9smGi

[vas3k @vas3kcom]

New post: Augmented Reality 😎

- What hardware and algorithms do we use to precisely track position
- How do we do light estimation and object occlusion
- What are the biggest challenges and where it all goes
- ARKit vs ARCore holywar is also there

https://t.co/zsd5Ljqp1R

[Sam Finlayson @IAmSamFin]

This is awesome! To be as explicit as possible: working through the examples and problems in this text is probably a strict superset of the training received in the grad-level intro to classical ML sequence at any top-caliber university.

[Daniel @DanielMatteF]

Why faces don’t always tell the truth about feelings https://t.co/0ioYTbMOip

[Daniel @DanielMatteF]

https://t.co/t08hWYKzeD

[Daniel @DanielMatteF]

Poxa. Morreu Larry Tesle, o criador do Copiar e Colar nos computadores. Pensa na quantidade de tempo que esse homem fez a humanidade economizar.

[Ramon Pires @piresramon]

Poxa. Morreu Larry Tesle, o criador do Copiar e Colar nos computadores. Pensa na quantidade de tempo que esse homem fez a humanidade economizar.