ICYMI, below are the https://t.co/ktYtgBpxGr results from April & post about our techniques.
— Rachel Thomas (@math_rachel) August 10, 2018
Post with today's results here: https://t.co/7pdbY1fBCF https://t.co/w736LtRZaK
ICYMI, below are the https://t.co/ktYtgBpxGr results from April & post about our techniques.
— Rachel Thomas (@math_rachel) August 10, 2018
Post with today's results here: https://t.co/7pdbY1fBCF https://t.co/w736LtRZaK
New, record-breaking speed results on ImageNet. Previous record was 30 mins using a TPU-pod by Google; now down to 18 mins on AWS by https://t.co/ktYtgBpxGr team! https://t.co/bEIMHOBn6M
— Rachel Thomas (@math_rachel) August 10, 2018
A small team of student AI coders beats Google’s machine learning code-- I am so proud of our https://t.co/ktYtgBpxGr students!!https://t.co/M9IvZvs8kn
— Rachel Thomas (@math_rachel) August 10, 2018
Nice! But it can equally be "Pro: a prior CAN be chosen"
— Sebastian Raschka (@rasbt) August 10, 2018
your regular reminder that the key to increasing diversity is to treat the women and people of Color who already work at your company very well: https://t.co/NkVc5Yseo9 pic.twitter.com/teQ4LGmbp5
— Rachel Thomas (@math_rachel) August 10, 2018
While people debated existence of saddle points and bad local minima, practitioners stared at graphs like below -- random initial starting point, but the final test accuracy is the same pic.twitter.com/rv9dIyUSjv
— Yaroslav Bulatov (@yaroslavvb) August 10, 2018
Next step in the development of fastai_v1: optimizer, training loop and callbacks! Here is a brief explanation of why we made it this way: https://t.co/D93YJ1IrqT
— Sylvain Gugger (@GuggerSylvain) August 10, 2018
Here are my slides from #APRADAS2018!https://t.co/1puBvdf9Yf
— Data Science Renee (@BecomingDataSci) August 10, 2018
This is a very thoughtful Q&A with Yoshua Bengio not only about starting a lab, but also about how to foster collaboration, network, and collaborate with industry. Definitely worth reading!https://t.co/3RicLRaG3w
— Sebastian Ruder (@seb_ruder) August 10, 2018
rant inspired by the following article: https://t.co/mChMlCncKm (which I liked but also found a bit negative! Author seems to echo the attitude they are complaining about rather than fighting it)
— Cian O'Donnell (@cian_neuro) August 10, 2018
Sorry folks I can tolerate these alchemy and pseudo-science claims any more. Here is my take on this: https://t.co/ZngbEpnrsA
— Leonid Boytsov (@srchvrs) August 10, 2018
Always enjoy seeing how data orgs are structured. @shane_m5 shows how the @nytimes has three overarching groups:
— Emily Robinson (@robinson_es) August 9, 2018
💻 data science: algorithms
📈 data analytics: metrics, experiments, exploratory analyses
🛠 data engineering: data platforms@RLadiesNYC Meetup pic.twitter.com/0ZvcrQMrvB