Max (@maxpumperla) has authored a book about using deep learning to play Go -- the code is open-source, and it uses Keras. Check it out: https://t.co/tiHGl1J4Fk
— François Chollet (@fchollet) August 30, 2018
Max (@maxpumperla) has authored a book about using deep learning to play Go -- the code is open-source, and it uses Keras. Check it out: https://t.co/tiHGl1J4Fk
— François Chollet (@fchollet) August 30, 2018
adversarial-autoencoders-tf - Tensorflow implementation of Adversarial Autoencoders https://t.co/yjQL0yh6ju
— Python Trending (@pythontrending) August 28, 2018
New seq2seq architecture - jointly encodes source and targets into a 2D ConvNet. No enc/dec or explicit attention.
— PyTorch (@PyTorch) August 27, 2018
Outperforming ConvS2S and Transformers on IWSLT'14 de<->en, with 3 to 8 times less parameters
from @melbayad and teamhttps://t.co/8NmiwmnhI2https://t.co/LqUYynj8vB pic.twitter.com/KFdcucErHI
The project is official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking" https://t.co/StFUBCUlYF #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience
— PyTorch Best Practices (@PyTorchPractice) August 25, 2018
#pytorch
Try out @NvidiaAI 's Vid2Vid project for photorealistic video-to-video translation, synthesizing label maps to realistic videos, people talking from edge maps, or generating human motions from poses
— PyTorch (@PyTorch) August 23, 2018
Now supports the latest PyTorch v0.4.1:https://t.co/vafmr7XQsf pic.twitter.com/XVu0vGQnLr
Great to see @fastdotai international fellows publishing their experimental results and code https://t.co/Va6yihdhCU
— Jeremy Howard (@jeremyphoward) August 21, 2018
NVIDIA's new vid2vid is the first open-source code that lets you fake anybody's face convincingly from one source video. prior "face2face" stuff was either cartoonish or proprietary. interesting times ahead... https://t.co/JsPVVa3xwa pic.twitter.com/AFhpeObd8N
— Gene Kogan (@genekogan) August 21, 2018
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
— ML Review (@ml_review) August 21, 2018
Outperforms SoTA encoder-decoder systems, while being conceptually simpler and having fewer parameters.
Githubhttps://t.co/QlSPJJZOFy
ArXivhttps://t.co/JjWpv9saG8 pic.twitter.com/GfTTNVZ54b
Blog post on adversarial reprogramming: https://t.co/jvPdXa9MUw pic.twitter.com/AxgP3E7eTM
— Ian Goodfellow (@goodfellow_ian) August 20, 2018
FFT-accelerated Interpolation-based t-SNE
— ML Review (@ml_review) August 19, 2018
By @GCLinderman
The most time-consuming step of t-SNE is accelerated by interpolating onto an equispaced grid and subsequently using the FFT to perform the convolution.
Paperhttps://t.co/aCL3Fmr0cn
Githubhttps://t.co/V4FTDdxPK1 pic.twitter.com/zxNxvmxQDi
Deep Convolutional Networks as shallow Gaussian Processes:https://t.co/oyoBqNJyfE
— fastml extra (@fastml_extra) August 17, 2018
Code:https://t.co/6x3Ru5TVLS
0.84% on MNIST! :P
Deep EHR: Chronic Disease Prediction Using Medical Notes from @narges_razavian, Jingshu Liu and Zachariah Zhang at NYU
— PyTorch (@PyTorch) August 16, 2018
Code & Tool: https://t.co/jEJ4aDfHhI
Read the paper at: https://t.co/uycxypYmdo pic.twitter.com/NDqccr2cYW