Understanding A Recurrent Neural Network For Image Generationby@shugert
4,274 reads

Understanding A Recurrent Neural Network For Image Generation

August 3rd 2019
17m
by @shugert 4,274 reads
tldt arrow
Read on Terminal Reader
Read this story w/o Javascript

Too Long; Didn't Read

Google Deepmind’s paper DRAW: A Recurrent Neural Network For Image Generation. The code is based on the work of Eric Jang, who in his original code was able to achieve the implementation in only 158 lines of Python code. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST.

People Mentioned

Mention Thumbnail

Companies Mentioned

Mention Thumbnail
Mention Thumbnail

Coin Mentioned

Mention Thumbnail
featured image - Understanding A Recurrent Neural Network For Image Generation
Samuel Noriega HackerNoon profile picture

@shugert

Samuel Noriega


Receive Stories from @shugert

react to story with heart

RELATED STORIES

L O A D I N G
. . . comments & more!