State-of-the-Art Deep Learning Models in TensorFlow: Modern Machine Learning in the Google Colab Ecosystem

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2021

D. PaperState-of-the-Art Deep Learning Models in TensorFlowhttps://doi.org/10.1007/978-1-4842-7341-8_9

9. Convolutional and Variational Autoencoders

David Paper¹  

(1)

Logan, UT, USA

 

Autoencoders don’t typically work well with images unless they are very small. But convolutional and variational autoencoders works much better than a feedforward dense ones with large color images.

A variational autoencoder (VAE) is a deep learning technique for learning latent representations. They apply learned latent space representations to draw images and interpolate between sentences. A VAE works by compressing the input into a latent space representation and then reconstructing ...