Thread of miscellaneous ICLR stuff I found potentially interesting (no particular order/theme) - some now, some later...
— Miles Brundage (@Miles_Brundage) September 28, 2018
Thread of miscellaneous ICLR stuff I found potentially interesting (no particular order/theme) - some now, some later...
— Miles Brundage (@Miles_Brundage) September 28, 2018
Code and paper available: https://t.co/ffWGvcJAxt
— Jeremy Howard (@jeremyphoward) September 28, 2018
Data mining reveals the hidden laws of evolution behind classical music https://t.co/E2t3S9Ei6n
— MIT Technology Review (@techreview) September 28, 2018
Train Wide-ResNet, Shake-Shake and ShakeDrop models on CIFAR-10 and CIFAR-100 dataset with AutoAugment. https://t.co/BFFGMOjyCF https://t.co/lJVxLh1jJL
— hardmaru (@hardmaru) September 28, 2018
Google Brain team researchers @ekindogus, @barret_zoph, and @quocleix have open sourced the AutoAugment image classification policies that achieve state-of-the-art results. Check out the the paper and code is located in tensorflow/models/research/autoaugment. #AutoML https://t.co/p4ZNxbzh5t
— Google AI (@GoogleAI) September 27, 2018
Github Engineering experiments with Semantic Code Search: search for code snippets using natural language.
— PyTorch (@PyTorch) September 26, 2018
Built on top of fastai + PyTorch, it's fully open-source
Read about their approach here: https://t.co/hWxlSUZIF5
Online Demo: https://t.co/ngdO0Vm6XQ pic.twitter.com/CqU77QGLsv
Wow! This is cool https://t.co/onjjjEv6xz
— Nando de Freitas (@NandoDF) September 26, 2018
A little post about mixup (https://t.co/YyOoM9ACAS) and how it allowed us to better our training time on CIFAR-10 in fastai_v1 (one GPU, 94% accuracy, 6 minutes):https://t.co/USgm0Ev08y
— Sylvain Gugger (@GuggerSylvain) September 24, 2018
AI Poker beat humans for the first time in two simultaneous-ish projects: DeepStack & Libratus, both of which use Counterfactual Regret Minimization. Good intro post for CRM, starting from Game Theory basics:
— Reza Zadeh (@Reza_Zadeh) September 23, 2018
Blog: https://t.co/93hDMz7RLp
Code: https://t.co/m5XEeZjGj6 pic.twitter.com/5BpuORj7tc
Generating 3D Adversarial Point Clouds. Cool new work showing how to hack PointNet-style classifiers. https://t.co/sDc60Qaygu #computervision #robotics pic.twitter.com/mrobOXuLBm
— Tomasz Malisiewicz (@quantombone) September 20, 2018
Using machine learning to predict restaurant affinities and preferences – the model from @Susan_Athey and colleagues https://t.co/La04DD7JfQ on @SafeGraph data https://t.co/JMvMciE7Xh
— Stanford NLP Group (@stanfordnlp) September 19, 2018
Totally missed posting the link: https://t.co/YjXZewMkrJ
— Sebastian Ruder (@seb_ruder) September 19, 2018