We're launching a Transcribe feature in Google Translate that can convert speech into another language as it’s happening. Starting in 8 languages, rolling out to Android today, more to come soon. #GoogleAIhttps://t.co/IMWjFgScVx
— Sundar Pichai (@sundarpichai) March 17, 2020
New tutorial!🚀
— Adrian Rosebrock (@PyImageSearch) March 16, 2020
Today I'm sharing a deeply personal post on Detecting #COVID19 in X-ray images with #Keras and #TensorFlow 2.0:https://t.co/ebHezQ38Y3 👍#DeepLearning #Python #MachineLearning #ArtificialIntelligence #DataScience
See rest of thread below for more info 1/11 pic.twitter.com/IDch6HpNRH
Curios how does the state of the art image classification training pipeline looks?
— Vladimir Iglovikov (@viglovikov) March 11, 2020
Check this video by @kaggle Grandmaster Arthur Kuzin.
"Bag of Tricks for Image Classification".
Slides: https://t.co/7Wg7uCYne3
Presentation: https://t.co/pAeVGF7ENP
New tutorial!🚀
— Adrian Rosebrock (@PyImageSearch) March 9, 2020
Implementing Grad-CAM with #Keras and #TensorFlow 2.0:
- Visualize where your CNN is "looking"
- Debug your CNNs
- Better model interpretabilityhttps://t.co/Aymt6WHJCZ 👍#Python #DeepLearning #MachineLearning #ArtificialIntelligence #AI #DataScience pic.twitter.com/eLigAycEXb
arXiv link: https://t.co/u7i5aPCyMU
— hardmaru (@hardmaru) March 2, 2020
Code: https://t.co/lTvtuqeqny
CookGAN: Meal Image Synthesis from Ingredients
— roadrunner01 (@ak92501) February 27, 2020
pdf: https://t.co/T63W7JVxEj
abs: https://t.co/8TI8WY80rL pic.twitter.com/PMIoJdgZES
The usual reason for filter bubbles is engineers throwing a bunch of features into a model without thinking carefully about the effects and not taking steps to prevent stereotyping.
— Arvind Narayanan (@random_walker) February 24, 2020
Here someone had to explicitly write code to stereotype people based on appearance.
Innovation! https://t.co/V2peZMygoI
"Trace precedents" in @msexcel is a great way to visualize the receptive field of a convnet. We'll be using this trick in our upcoming book and next course in San Francisco. The green cell is activation, blue square receptive field https://t.co/guKT7y9VfMhttps://t.co/bLd3sEXTpV pic.twitter.com/iZpXspd3Vg
— Jeremy Howard (@jeremyphoward) February 24, 2020
Beauty in the digital age 💄⚡
— TensorFlow (@TensorFlow) February 24, 2020
Check out how @ModiFace utilized #TensorFlowJS to allow users to try on AR makeup in the browser!
Read the blog → https://t.co/Hj0puksfGw pic.twitter.com/z8M4CIWf2J
KaoKore: A Pre-modern Japanese Art Facial Expression Dataset
— hardmaru (@hardmaru) February 21, 2020
Labelled faces extracted from pre-modern Japanese artwork! Allows for fun ML experiments, like Intrinsic Style Transfer + Learning to Paint.
Researchers are probably “commoners” in Edo-Period.https://t.co/9JlRjJQLiY pic.twitter.com/RTcmwwDvHL
It's hard to unsee, but this is a model effort at it! https://t.co/CRQrXRJyta
— Jeff Dean (@JeffDean) February 18, 2020
Students are getting REALLY advanced with their cheating nowadays.
— Randy Olson (@randal_olson) February 13, 2020
This project uses #Python + #OCR to look up the answers to high school textbook problems almost instantly.
Video source: https://t.co/rk9TU3mKq8
Code source: https://t.co/VgEp7Nf7NN #programming pic.twitter.com/PoQeEJkz3g
