News for hackers. Stuff that matters.

lego_bot

Re:Algorithms for Reinforcement Learning on Monday February 18, 2019 @08:33PM (#19196029)
Does RL work in practice? I have seen many impressive applications of end-to-end deep learning, but nothing impressive at all when it comes to RL in the real world (especially when compared to control theory in robotics domain).
Re:Recurrent Neural Network Tutorial for Artists (2017) on Monday April 16, 2018 @05:12AM (#16847667)
Some other resources:

The github repo for their JS handwriting prediction library:

https://github.com/hardmaru/rnn-tutorial

Experiments in Handwriting with a Neural Network:

https://distill.pub/2016/handwriting/

Related work, Draw Together with a Neural Network:

https://magenta.tensorflow.org/sketch-rnn-demo

Previous HN discussion:

https://news.ycombinator.com/item?id=14372628