The Intuition behind Adversarial Attacks on Neural Networks
— ML Review (@ml_review) April 1, 2019
By @anant90
Trade-off between trainability and robustness to adversarial attacks:
Ease of optimisation has come at the cost of models that are easily misledhttps://t.co/cRaSJyj7q9 pic.twitter.com/pZtSaQQCNS
"How to do FastAI even faster: Speed up preprocessing using fastai’s built in ‘parallel’ function"
— Jeremy Howard (@jeremyphoward) March 20, 2019
Nice introduction to a handy little helper function.https://t.co/buji9oTsLj pic.twitter.com/bMx9Hrh62w
Looks like a great overview of the area: "Algorithms for Verifying Deep Neural Networks," Liu et al.: https://t.co/xjCb0ZBuUG
— Miles Brundage (@Miles_Brundage) March 19, 2019
Every generation of ML researchers needs to relearn the lessons of this paper. https://t.co/5mOAm0ruED
— David Pfau (@pfau) March 15, 2019
Learn more about the #PoweredByTF ML model that ranks the tweets in your timeline! The Cortex and Home Timeline teams at @Twitter describe re-tooling their platform for TensorFlow in this guest post. #TFDevSummit
— TensorFlow (@TensorFlow) March 7, 2019
Read it here ↓ https://t.co/frYDPaIvCj
Mastering Fast Gradient Boosting on Google Colaboratory with free GPU
— ML Review (@ml_review) February 28, 2019
By @besab @CatBoostML
Many think GBDT cannot be efficiently accelerated by a GPU, but this is actually not true.
Yandex CatBoost runs 4x faster on Tesla K80 vs Intel Xeon E5–2600v3 https://t.co/TJ5gg9tkld pic.twitter.com/PTEdlMBnHn
In the meantime, here are the slides from my PhD defence presentation on Neural Transfer Learning for Natural Language Processing: https://t.co/abYFX5zXXq
— Sebastian Ruder (@seb_ruder) February 27, 2019
Amazing review paper to help you make sense of the latest algorithmic advances and how they’ve been applied to various game environments. Must’ve been incredibly difficult to keep up with all the progress. The table and figures in this paper are great! https://t.co/mQHtBfiNCu
— Denny Britz (@dennybritz) February 20, 2019
A no-hype, no-math introduction to (arguably) the most important advance in modren NLP: https://t.co/o3ehWKs4kG. Simple, accessible, and informative by @nlpnoah cc @stanfordnlp
— Oren Etzioni (@etzioni) February 20, 2019
Generating Textual Adversarial Examples for Deep Learning Models: A Survey
— ML Review (@ml_review) February 4, 2019
By @Macquarie_Unihttps://t.co/SZkFlZSvsF pic.twitter.com/R7FRUcfJtD
This post from @realAKJackson is a wonderful way to use a blog. Takes hard-earned experience- here, the differences in accuracy between free geocoding engines- and shares it with everyone
— David Robinson (@drob) January 31, 2019
Conclusions, code, concrete examples 🗺️👏https://t.co/jKsxjBui4L #rstats #datablog pic.twitter.com/c0yg57CrFm
That's great. But this is still better:
— Dan ofer (@danofer) January 18, 2019
"A Few Useful Things to Know about Machine Learning"https://t.co/HRo1GyfsOv
