Robots and deep learning to solve recycling challenges. Great new application. https://t.co/EhpgKYjI20
— Nando de Freitas (@NandoDF) July 28, 2019
Robots and deep learning to solve recycling challenges. Great new application. https://t.co/EhpgKYjI20
— Nando de Freitas (@NandoDF) July 28, 2019
Trading via Image Classification
— ML Review (@ml_review) July 25, 2019
By @jpmorgan @tuckerbalch
Explicitly represent time-series data as images. Inspired by traders that always execute their trade observing images of financial time-series on screenshttps://t.co/I0fnGFbVHA pic.twitter.com/veGmsPaXBX
Architecture meets AI. ArchiGAN is an app that uses #Pix2Pix and TensorFlow to generate floor plans.
— TensorFlow (@TensorFlow) July 24, 2019
See how it’s done on the @NVIDIA blog → https://t.co/8LGVyI71iU
Try Pix2Pix yourself → https://t.co/5QODTeNppR pic.twitter.com/UQ03tCmdKi
Autocompletion with deep learning https://t.co/WenacHVj7z very cool! I tried related ideas a long while ago in days of char-rnn but it wasn't very useful at the time. With new toys (GPT-2) and more focus this may start to work quite well. pic.twitter.com/XSV9O7yxpf
— Andrej Karpathy (@karpathy) July 18, 2019
A short introduction to the @abraham_ai_ project to study and build an autonomous artificial artist https://t.co/xbRtVd5FkG
— Gene Kogan (@genekogan) July 16, 2019
Deep learning based super resolution, without using a GAN https://t.co/2CI0RoT0EY
— Jeremy Howard (@jeremyphoward) July 15, 2019
Learn about SmileAR and @iQIYIofficial's experience using TensorFlow Lite for gesture recognition, pose estimation, and more in this guest post by the iQIYI engineering team.
— TensorFlow (@TensorFlow) July 12, 2019
Read here ↓ https://t.co/dwVUtWI5NG
Create your own Magic: The Gathering cards with AI! Give a card name, card type, and/or card mana cost to a finetuned GPT-2, and get a custom card image + card text! https://t.co/OdvF4X9QID pic.twitter.com/TUFf9ISwz0
— Max Woolf (@minimaxir) July 9, 2019
This AI was able to correctly identify manipulated images 99% of the time, compared to a 53% success rate for humans. https://t.co/OeodgJiz8H
— MIT Technology Review (@techreview) June 20, 2019
This is an AWESOME use for machine learning: “defragging” calendars to give back blocks of uninterrupted time! Brilliant. I want this. https://t.co/qvJG1XFBAK
— Tim O'Reilly (@timoreilly) June 17, 2019
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time https://t.co/ymHvCJjC9y
— Python Trending (@pythontrending) June 17, 2019
We've spent a few evenings last week building an interactive demo called *Write with Transformer*
— Thomas Wolf (@Thom_Wolf) June 13, 2019
It lets you interact in a very intimate way with GPT-2, call, control, question the model... and I just can't stop playing with it!
You can try it at https://t.co/EZhtCodnoi https://t.co/me75uCeJ9q