CoralNet evaluated by NOAA.
— Yann LeCun (@ylecun) April 30, 2019
ConvNets can be used to quantify the health of coral reefs.
Congrats David Kriegman https://t.co/a2cJKQY76F
CoralNet evaluated by NOAA.
— Yann LeCun (@ylecun) April 30, 2019
ConvNets can be used to quantify the health of coral reefs.
Congrats David Kriegman https://t.co/a2cJKQY76F
A series of blog posts on applying machine learning to architecture
— hardmaru (@hardmaru) April 30, 2019
Experiments: https://t.co/zhmOsAjeaE
Background: https://t.co/6lqeJQN980 pic.twitter.com/LzivM1PauQ
Speedgate is a sport "invented" by neural networks. It serves as a fun demo of the sort of creative process you can achieve by combining ML-generated suggestions with human curation and refinement. Made with Keras! https://t.co/g6ud45H8BZ
— François Chollet (@fchollet) April 26, 2019
Announcing our "Song of the Day" contest: create your own MuseNet composition (https://t.co/P0EQbRmQ8O), upload it to a hosted service https://t.co/pilBpdBfaM, and tweet it to @openai w/ the tag #MuseNet.
— OpenAI (@OpenAI) April 25, 2019
We'll announce a new winner each day for the next week. It could be you! pic.twitter.com/Csdwe42qqW
OpenAI just released MuseNet, a transformer-based model that can generate music with 10 instruments in a bunch of styles. Something I learned from playing around the embedding viz = The Beatles have something in common with composer Franck & Tchaikovsky!https://t.co/yhSYC0U8TP pic.twitter.com/yGignFs4TU
— Jack Clark (@jackclarkSF) April 25, 2019
https://t.co/OnrSfijYp7, a startup that uses GANs to generate retail marketing images, has raised $17M: https://t.co/msb3fOsGw4
— Ian Goodfellow (@goodfellow_ian) April 25, 2019
Decoding (EEG) brain signals to synthesize speech
— Adam J Calhoun (@neuroecology) April 24, 2019
tl;dr mind reading what someone wants to say (!!) https://t.co/JryxOZuyxE pic.twitter.com/ir5TIqFt8a
This is the most terrifying ML application I've seen in a while:https://t.co/M047AVDLh9
— Joel Grus ☕ (@joelgrus) April 23, 2019
Using Transformer models to generate Hacker News comments from titles.
— hardmaru (@hardmaru) April 23, 2019
Fun demo: https://t.co/pGfnObA9gX pic.twitter.com/j0YQIb3Uuu
Predicting future medical diagnoses with RNNs using Fast AI API from scratch
— Rachel Thomas (@math_rachel) April 22, 2019
(full pytorch implementation of Doctor AI paper using Electronic Health Records) by @SparklePuleri https://t.co/a2wmQEQ7Cg
Exciting work showing the potential of the methodology introduced in https://t.co/aQsW5afov6 lesson 7 to reduce negative impact of out-of-focus microscopy images! :) https://t.co/KKkOEVObPf
— Jeremy Howard (@jeremyphoward) April 22, 2019
Aroma: code-to-code search and recommendation system from Facebook AI. https://t.co/Ix2TXDgqES
— Yann LeCun (@ylecun) April 9, 2019