DSpace Repository

Augmenting GAN with continuous depth Neural ODE

Show simple item record

dc.contributor.author Varshney, Love
dc.date.accessioned 2022-02-02T05:03:13Z
dc.date.available 2022-02-02T05:03:13Z
dc.date.issued 2019-07
dc.identifier.citation 24p. en_US
dc.identifier.uri http://hdl.handle.net/10263/7260
dc.description Dissertation under the supervision of Prof. Sushmita Mitra, MIU en_US
dc.description.abstract Generative adversarial networks are extremely powerful tools for generative modeling of complex data distributions. Research is being actively conducted towards further improving them as well as making their training easier and more stable. In this thesis, we present Neural ODE Generative Adversarial Network (NGAN), a framework that uses Neural ODE blocks instead of the standard convolutional neural networks (CNNs) as discriminators and generators within the generative adversarial network (GAN) setting. We show that NGAN outperforms convolutional-GAN at modeling image data distribution on MNIST dataset, evaluated on the generative adversarial metric. iii en_US
dc.language.iso en en_US
dc.publisher Indian Statistical Institute, Kolkata en_US
dc.relation.ispartofseries Dissertation;;2019:12
dc.subject GAN en_US
dc.subject Cost function en_US
dc.title Augmenting GAN with continuous depth Neural ODE en_US
dc.type Other en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account