MangaCraft is a tool to help colorize any kind of manga without much domain expertise. https://t.co/6HkFA6tgs2 pic.twitter.com/N2PheMQxeA
— hardmaru (@hardmaru) September 19, 2018
MangaCraft is a tool to help colorize any kind of manga without much domain expertise. https://t.co/6HkFA6tgs2 pic.twitter.com/N2PheMQxeA
— hardmaru (@hardmaru) September 19, 2018
Style2paints is a neat deep learning-based line-art colorization program developed using Keras: https://t.co/BBsQml7Xoq
— François Chollet (@fchollet) September 18, 2018
Its creator is now turning it into a more ambitious project to increase the productivity of coloring workflows: MangaCraft https://t.co/MsP03B4z2N pic.twitter.com/QQUc8HpFST
There is now an official notebook from @DeepMindAI on Conditional Neural Processes: https://t.co/Yt7HAQ64UE #flames 🔥 https://t.co/0NwQVcjV3N
— Kaixhin (@KaiLashArul) September 18, 2018
This line of research will be of interest to the development of spike-based neuromorphic chips that consume much less power compared to traditional processors.
— hardmaru (@hardmaru) September 18, 2018
Corrected link: https://t.co/zzxhi2Gzal
— hardmaru (@hardmaru) September 17, 2018
This paper just came to my attention (and I can't forgive myself for not seeing it earlier) https://t.co/BHbKcaWotl
— Judea Pearl (@yudapearl) September 16, 2018
A friendly, comprehensive and unifying (no hangups) roadmap to epidemiological methodology. Highly recommended. #Bookofwhy#causalinference @EpiEllie @miquelporta
For unconditional generation (producing good samples/likelihoods), these two papers are worth knowing about:
— Sam Bowman (@sleepinyourhat) September 15, 2018
– https://t.co/skhHFkfcQ4
– https://t.co/98VW8asmTp
Thanks, but I wouldn't agree—VAEs are a very interesting model to work with, and they show up as a piece of cool larger models, but our paper is a pretty robust/reproducible _negative_ result. Plain VAEs are no better than plain LSTM language models by any standard measure.
— Sam Bowman (@sleepinyourhat) September 15, 2018
@sleepinyourhat 's VAE is actually really strong https://t.co/EPJ0CqH5fa
— Marc Rosenberg (@Make3333) September 15, 2018
Implementation of Everybody Dance Now by pytorch https://t.co/8etHXuQyVZ #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) September 15, 2018
If you like char-rnn, try char-transformer: https://t.co/meYyzEWz93
— hardmaru (@hardmaru) September 15, 2018
Ah, alas :p. This might be a fun thing to play with: https://t.co/INR7uBe52T
— Matthew Honnibal (@honnibal) September 14, 2018
The big thing in NLP at the moment is language modelling, e.g. https://t.co/OWknRzGvXC
This is my NN-for-NLP 101: https://t.co/lU8HEK3YZI