| Tweetovi |
| Jay Bhatt proslijedio/la je tweet | ||
|
Andrej Karpathy
@karpathy
|
1. lip |
|
Speech2Face: Learning the Face Behind a Voice speech2face.github.io With increasingly large/effective library of neural net encoders of any X and decoders of any Y, any source of paired data X,Y can give X2Y nets. And opens the door to many X2Y2Z2W...2X
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
François Chollet
@fchollet
|
28. tra |
|
Training ever bigger convnets and LSTMs on ever bigger datasets gets us closer to Strong AI -- in the same sense that building taller towers gets us closer to the moon.
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
DeepMind
@DeepMind
|
3. tra |
|
Today we're releasing a large-scale extendable dataset of mathematical questions, for training (and evaluating the abilities of) neural models that can reason algebraically.
Paper: arxiv.org/abs/1904.01557
Code and data: github.com/deepmind/mathe… pic.twitter.com/EWqNqaOUd5
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
François Chollet
@fchollet
|
11. ožu |
|
Are you a deep learning researcher? Wondering if all this TensorFlow 2.0 stuff you heard about is relevant to you?
This thread is a crash course on everything you need to know to use TensorFlow 2.0 + Keras for deep learning research. Read on! pic.twitter.com/dFNI2E6yjF
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
François Chollet
@fchollet
|
5. ožu |
|
Using Keras for "thought reading" (subvocalized word classification from EEG signals): medium.com/@justlv/using-… 🧠
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
hardmaru
@hardmaru
|
4. ožu |
|
Using deep learning to implement linear regression twitter.com/MachinePix/sta…
|
||
|
|
||
|
Jay Bhatt
@Jay_Bhatt_007
|
8. sij 2019. |
|
When do you wanna start bro?
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
Yann LeCun
@ylecun
|
20. pro 2018. |
|
NeverGrad: gradient free optimization library. Now open source. code.fb.com/ai-research/ne…
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
PyTorch
@PyTorch
|
26. stu 2018. |
|
Microsoft VSCode integrates deeply with PyTorch out of the box.
As @aerinykim highlights:
1. It shows values inside tensors. (Left panel)
2. By simply mousing over, you can see the variable's shape, weight, bias, dtype, device, etc.
code.visualstudio.com pic.twitter.com/voxEO50bl7
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
Mike Tyka
@mtyka
|
15. stu 2018. |
|
Using GANs to generate Master[Finger]Prints that unlock 22-78% phones sensors (dep. on security level of sensor) arxiv.org/pdf/1705.07386… .. doesn't get much more "adversarial" than that. pic.twitter.com/zZMyDBDBHf
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
DeepMind
@DeepMind
|
25. ruj 2018. |
|
Today we are open-sourcing our code for "The mechanics of n-player differentiable games"!
Code: github.com/deepmind/sympl…
Original paper: proceedings.mlr.press/v80/balduzzi18…
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
Minsuk Kahng
@minsukkahng
|
4. ruj 2018. |
|
Excited to announce GAN Lab! Interactive visualization to learn #GAN by @GoogleAI @gtcomputing, powered by @TensorFlow.js! Try in your browser poloclub.github.io/ganlab/
Great collaboration with @nsthorat @polochau @viegasf @wattenberg!
@ieeevis'18 paper: goo.gl/R9gUKy pic.twitter.com/S5DSjotClx
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
Google AI
@GoogleAI
|
5. ruj 2018. |
|
Announcing the launch of Dataset Search, a new way for researchers to find the datasets they need, wherever they’re hosted, whether it’s a publisher's site, a digital library, or an author's personal web page. Learn more at goo.gl/BYSouA pic.twitter.com/kvlmDOHSO1
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
TensorFlow
@TensorFlow
|
2. kol 2018. |
|
It's been our goal since we launched to run on as many platforms as possible. We're happy to announce that it's now easier than ever to install TensorFlow on your @RaspberryPi!
Learn more in @petewarden's post ↓ bit.ly/2OFsI7N
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
Yann LeCun
@ylecun
|
20. srp 2018. |
|
Unsupervised pre-training is starting to work quite well for learning visual representations.
Here is a new paper from FAIR-Paris that demonstrates how this works. facebook.com/yann.lecun/pos…
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
TensorFlow
@TensorFlow
|
13. srp 2018. |
|
This paper includes 15 TensorFlow Hub modules to generate images using GANs! Check out the colab notebook to try it out → bit.ly/2NPDtEg #TFHub twitter.com/GoogleAI/statu…
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
Jascha
@jaschasd
|
1. srp 2018. |
|
Adversarial Reprogramming of Neural Networks goo.gl/qnB5FA A new goal for adversarial attacks! Rather than cause a specific misclassification, we force neural networks to behave as if they were trained on a completely different task! With @gamaleldinfe, @goodfellow_ian pic.twitter.com/1Wj8aOIHn5
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
hardmaru
@hardmaru
|
27. lip 2018. |
|
Guided Evolutionary Strategies: Escaping the curse of dimensionality in random search, from Google Brain: @Niru_M @Luke_Metz @GeorgeJTucker @JaschaSD.
Paper: arxiv.org/abs/1806.10230
GitHub: github.com/brain-research…
Notebook: colab.sandbox.google.com/github/brain-r… pic.twitter.com/HIGEEi7FkN
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
François Chollet
@fchollet
|
25. sij 2018. |
|
If you're interested in autonomous vehicles, Microsoft has released a tutorial (with complete Keras code) for training an end-to-end driving model in the AirSim simulation environment: github.com/Microsoft/Auto… pic.twitter.com/15N6PmBNcQ
|
||
|
|
||
| Jay Bhatt proslijedio/la je tweet | ||
|
Marques Brownlee
@MKBHD
|
27. sij 2018. |
|
Random weekend thought: The human body would make an amazing camera. Our necks are great stabilizers. Shutter speed is always perfect. Eyeballs have incredible dynamic range and really fast autofocus... Just needs better memory.
|
||
|
|
||