Variational Autoencoders Explained. August, 2016.
Variational Autoencoders Explained [link]Paper  abstract   bibtex   
In my previous post about generative adversarial networks, I went over a simple method to training a network that could generate realistic-looking images. However, there were a couple of downsides to using a plain GAN. First, the images are generated off some arbitrary noise. If you wanted to generate a
@misc{noauthor_variational_2016,
	title = {Variational {Autoencoders} {Explained}},
	url = {http://kvfrans.com/variational-autoencoders-explained/},
	abstract = {In my previous post about generative adversarial networks, I went over a simple method to training a network that could generate realistic-looking images. However, there were a couple of downsides to using a plain GAN. First, the images are generated off some arbitrary noise. If you wanted to generate a},
	urldate = {2018-05-04TZ},
	journal = {kevin frans},
	month = aug,
	year = {2016},
	keywords = {\#Introductory Overview, AI=Artificial Intelligence, Algorithms, Classification, Computer Science, Computer Vision, Data Science, GAN=Generative Adversarial Network, Image Analysis, Informatics, Machine Learning, Machine Learning Applications, Neural Networks, Source Code, Statistics - Machine Learning, Variational Autoencoders, Working Code}
}
Downloads: 0