Autoencoders are neural networks that are capable of creating sparse representations of the input data and can therefore be used for image compression. There are denoising autoencoders that after learning these sparse representations, can be presented with noisy images. What is even better is a variant that is called the variational autoencoder that not only learns these sparse representations, but can also draw new images as well. We can, for instance, ask it to create new handwritten digits and we can actually expect the results to make sense!
_____________________________
The paper “Auto-Encoding Variational Bayes” is available here:
Recommended for you:
Recurrent Neural Network Writes Sentences About Images –
Andrej Karpathy’s convolutional neural network that you can train in your browser:
Sentdex’s Youtube channel is available here:
Francois Chollet’s blog post on autoencoders:
More reading on autoencoders:
WE WOULD LIKE TO THANK OUR GENEROUS PATREON SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE:
David Jaenisch, Sunil Kim, Julian Josephs, Daniel John Benton, Dave Rushton-Smith, Benjamin Kang.
We also thank Experiment for sponsoring our series. –
Subscribe if you would like to see more of these! –
Music: Dat Groove by Audionautix is licensed under a Creative Commons Attribution license (
Artist:
Thumbnail background image source (we have edited the colors and edited it some more):
Splash screen/thumbnail design: Felícia Fehér –
Károly Zsolnai-Fehér’s links:
Facebook →
Twitter →
Web →
source
