@inproceedings{witte2021invertiblenetworks,
author = {Witte, Philipp and Louboutin, Mathias and Siahkoohi, Ali and Herrmann, Felix J. and Rizzuti, Gabrio and Peters, Bas},
title = {InvertibleNetworks.jl - Memory efficient deep learning in Julia},
booktitle = {JuliaCon 2021},
year = {2021},
month = {July},
abstract = {We present InvertibleNetworks.jl, an open-source package for invertible neural networks and normalizing flows using memory-efficient backpropagation. InvertibleNetworks.jl uses manually implement gradients to take advantage of the invertibility of building blocks, which allows for scaling to large-scale problem sizes. We present the architecture and features of the library and demonstrate its application to a variety of problems ranging from loop unrolling to uncertainty quantification.},
url = {http://approjects.co.za/?big=en-us/research/publication/invertiblenetworks-jl-memory-efficient-deep-learning-in-julia/},
}