S N

[🟨 E-jacca @e_jacca]

��검은토끼 토야를 잡아라!
베이비핑이 와그미포스트에서 열었던 이벤트의 당첨자를 발표합니다.
상위 3분께는 NFT룰 보내드리며, 차상위 2분께는 와그미 다이아 50개씩을 보내드려요~
많은 관심과 사랑 감사드리며,
앞으로도 쭈욱~ 많관부😘
@BabypingNFT @wagmipost

[Google DeepMind @GoogleDeepMind]

Transformers have shown remarkable capabilities - but can they improve themselves autonomously from trial and error?

New research shows how a single transformer can explore and solve tasks using this method without ever updating its parameters ➡️ https://t.co/8af0uOIzBl

[PyTorch Best Practices @PyTorchPractice]

Develop like a Pro with NVIDIA + Docker + VS Code + PyTorch https://t.co/gTAVPazc48
#deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #PyTorch

[Lightning AI ⚡️ @LightningAI]

Lightning Pose: Convolutional Networks for pose tracking implemented in PyTorch Lightning, supporting massively accelerated training on unlabeled videos using NVIDIA DALI.

We totally agree that Lightning is one of the coolest DL packages around. 😎

Repo: https://t.co/OoVs5U4Fmc

[S N @WindFlow80]

@Swave0314 @areal4519 @Vowy15

[코인버핏 (Coinbuffett)&덕PD(DuckPD)❤️ $WELL @coin_buffett]

[더솔져스NFT X 코인버핏 ]

-더솔져스NFT X 코인버핏 구독자 이벤트
NFT 2명 (100만원상당) +화리 10명 DROP

1.코인버핏 트위터 팔로우 후 리트윗 친구3명이상 태그

2.https://t.co/okXSj86U5f
유튜브 영상에 아무글 or 영상 후기 댓글 남기고 구글폼(유튜브확인) 제출

#더솔져스NFT #더솔져스

[S N @WindFlow80]

@MetaCats_club @KlayRabbit @areal4519 @Vowy15 @Swave0314

[S N @WindFlow80]

@MetaCats_club @KlayLandforAll @Swave0314 @areal4519 @Vowy15

[S N @WindFlow80]

@MeeCatsClub @Swave0314 @areal4519 @Vowy15

[Robin Lobel @divideconcept]

On April 21st I'll be presenting https://t.co/NCly5F5WT8, a machine learning studio based on @PyTorch at the Pytorch Ecosystem Day. Register now at https://t.co/Vo4ZSOsBLA ! #PTED21 #PyTorch #DeepLearning #AI

[David Duvenaud @DavidDuvenaud]

We just open-sourced differentiable SDE solvers in PyTorch:
https://t.co/v1f08mjgCq
Now you can put stochastic differential equations in your deep learning models, and neural nets in your SDEs! Credit to @lxuechen.

[PyTorch @PyTorch]

Optuna is a black-box optimizer. Learn how you can use Optuna to create the objective function, define the hyperparameters, run trials, and perform pruning to optimize PyTorch hyperparameters.

https://t.co/2U6vsZEg6K

[Mingxing Tan @tanmingxing]

Excited to announce the open source of EfficientDet: better accuracy & efficiency on COCO detection. Bonus: it also works pretty well for semantic segmentation (Table 3)!

Paper: https://t.co/tO1mtfuaKx
Code: https://t.co/pzfNoM6IS5

[Pieter Abbeel @pabbeel]

Want to learn some modern robotics?

All lecture videos from CS287 Advanced Robotics Fall'19 offering are now available online.

https://t.co/zWWhdATokc

[Leandro von Werra @lvwerra]

I built my first python package: jupyterplot! Plot real-time results in Jupyter notebooks.

https://t.co/KGk1YZWJWW

It is founded on @andreas_madsen's excellent python-lrcurve library.

Effortless development and publishing with #nbdev by @jeremyphoward and @GuggerSylvain.

[DeepAI @DeepAI]

Learn about Radial Basis Function Networks https://t.co/eWTeDluiTK #Vector #RadialBasisFunctionNetworks

[AI at Meta @AIatMeta]

Facebook AI is open-sourcing a new, easy-to-use, end-to-end framework for large-scale, state-of-the-art image and video classification tasks. It enables anyone to train models on top of @PyTorch using very simple abstractions. #NeurIPS2019
https://t.co/0wAf2fqXQK

[Sergey Levine @svlevine]

Can we use deep RL to learn from data, rather than from online interaction? Aviral Kumar discusses challenges and recent work in this area, including our algorithm BEAR for fully-off policy RL: https://t.co/XUYxsE3mNK

[SOAI.world @soaiworld]

Want to learn the Math required to understand deep learning before learning Keras? https://t.co/ZVkd3a5fxs

[PyTorch @PyTorch]

3-Step Transfer Learning using @huggingface Transformers and @PyTorchLightnin training framework.
A step-by-step post by @williamfalcon
https://t.co/zD0rm5u6Hz

[AI at Meta @AIatMeta]

1/4: The lottery ticket hypothesis suggests that by training DNNs from “lucky” initializations, we can train networks which are 10-100x smaller with minimal performance losses. In new work, we extend our understanding of this phenomenon in several ways... https://t.co/fbEKjgeG6Y