Top news of the week: 28.05.2020.
Neural network, Knowledge engineering, The Network, Autonomous robot, Quantum entanglement, Machine learning
Research
RT @kdnuggets: The Best NLP with Deep Learning Course is Free - KDnuggets https://t.co/vE0qhZPHAT https://t.co/v06RqwEL4q
OpenThe Best NLP with Deep Learning Course is Free
Stanford's Natural Language Processing with Deep Learning is one of the most respected courses on the topic that you will find anywhere, and the course materials are freely available online.
RT @ethanachi: Does Multilingual BERT share syntactic knowledge cross-lingually? In #acl2020nlp paper w/ @johnhewtt and @chrmanning, we visualize its syntactic structure & show it's applicable to a variety of human languages.
Paper: https://t.co/hUo5o6oZSL
Blog: https://t.co/oeTnwMfz62 (1/4) https://t.co/y7TQYfx2Op
OpenFinding Cross-Lingual Syntax in Multilingual BERT
We projected head-dependent pairs from both English (light colors) and French (dark colors) into a syntactic space trained on solely English mBERT representations. Importantly, …
Tips for Research and a PhD by @seb_ruder
TL;DR:
• Read broadly
• Work on 2 things
• Be ambitious
• Collaborate
• Be proactive
• Blog
• Keep a source of positive energy
• Play to your strengths
• Intern / visit a university
• Play the long game https://t.co/jk5wpzf9dB
Open10 Tips for Research and a PhD
This post outlines 10 things that I did during my PhD and found particularly helpful in the long run.
RT @zoink: For the first time, I'm sharing the @thielfellowship application from December, 2011 which eventually led to @figmadesign.
My hope is that this inspires others to pursue entrepreneurial paths, even if they don't have the "perfect idea" just yet!
https://t.co/X4LiT2rbp8
OpenFigma’s Story, Part 1: My Thiel Fellowship Application (2011)
When I talk with entrepreneurs that are just starting off, I’m often asked about how Evan and I came up with the idea for Figma. Here’s the short answer: During my Flipboard internship I ...
RT @hari: Nvidia’s AI recreates Pac-Man from scratch just by watching it being played - https://t.co/NWOTJTUmxl by @jjvincent Pac-Man today... "Shall.. we... play a game?" tomorrow.
OpenNvidia’s AI recreates Pac-Man from scratch just by watching it being played
‘It learns all of these things just by watching’
We are proud to announce Paddle Quantum, a #quantum machine learning development toolkit for training quantum neural network models & supporting advanced #QuantumComputing applications.
Read more: https://t.co/tg2zwiA63P https://t.co/SpZ6THcLdB
OpenIntroducing Paddle Quantum: How Baidu's Deep Learning Platform PaddlePaddle Empowers Quantum Computing
We are proud to announce Paddle Quantum, a quantum machine learning development toolkit that can help scientists and developers quickly build and train quantum neural network …
awesome! "generative adversarial network trained on 50,000 PAC-MAN episodes, produces a fully functional [game] ... without an underlying game engine"
https://t.co/ZjWpZPonIT
Open40 Years on, PAC-MAN Recreated with AI by NVIDIA Researchers
On the 40th anniversary of PAC-MAN, NVIDIA GameGAN generated a fully functional version of the classic — without an underlying game engine.
RT @ducha_aiki: The third block of labs is about CNNs. That is completely done from scratch rather than migrating.
Lab1: training ImageNette (kudos to @jeremyphoward ).
To implement: the architecture of choice, lr_find @lnsmith613, training loop, one-cycle.
🧶
https://t.co/Iweat79N2h https://t.co/nleLGh6UFg
OpenConvolutional Neural Networks
Deep Convolutional Neural Networks (CNNs) re-entered into the computer vision community recently, especially after the breakthrough paper of Krizhevsky et al. This success …