DeepAI AI Chat
Log In Sign Up

Training Invertible Neural Networks as Autoencoders

by   The-Gia Leo Nguyen, et al.
University of Heidelberg

Autoencoders are able to learn useful data representations in an unsupervised matter and have been widely used in various machine learning and computer vision tasks. In this work, we present methods to train Invertible Neural Networks (INNs) as (variational) autoencoders which we call INN (variational) autoencoders. Our experiments on MNIST, CIFAR and CelebA show that for low bottleneck sizes our INN autoencoder achieves results similar to the classical autoencoder. However, for large bottleneck sizes our INN autoencoder outperforms its classical counterpart. Based on the empirical results, we hypothesize that INN autoencoders might not have any intrinsic information loss and thereby are not bounded to a maximal number of layers (depth) after which only suboptimal results can be achieved.


Quantization-Based Regularization for Autoencoders

Autoencoders and their variations provide unsupervised models for learni...

Subitizing with Variational Autoencoders

Numerosity, the number of objects in a set, is a basic property of a giv...


An autoencoder is a specific type of a neural network, which is mainlyde...

Stable training of autoencoders for hyperspectral unmixing

Neural networks, autoencoders in particular, are one of the most promisi...

Walking the Tightrope: An Investigation of the Convolutional Autoencoder Bottleneck

In this paper, we present an in-depth investigation of the convolutional...

EvoAAA: An evolutionary methodology for automated autoencoder architecture search

Machine learning models work better when curated features are provided t...

Distributed Evolution of Deep Autoencoders

Autoencoders have seen wide success in domains ranging from feature sele...