Search Results for author: Chandramouli Shama Sastry

Found 4 papers, 2 papers with code

Detecting Out-of-Distribution Examples with Gram Matrices

no code implementations ICML 2020 Chandramouli Shama Sastry, Sageev Oore

We find that characterizing activity patterns by Gram matrices and identifying anomalies in Gram matrix values can yield high OOD detection rates.

OOD Detection

Efficient CDF Approximations for Normalizing Flows

1 code implementation23 Feb 2022 Chandramouli Shama Sastry, Andreas Lehrmann, Marcus Brubaker, Alexander Radovic

Instead, we build upon the diffeomorphic properties of normalizing flows and leverage the divergence theorem to estimate the CDF over a closed region in target space in terms of the flux across its \emph{boundary}, as induced by the normalizing flow.

Musical Speech: A Transformer-based Composition Tool

no code implementations2 Aug 2021 Jason d'Eon, Sri Harsha Dumpala, Chandramouli Shama Sastry, Dani Oore, Sageev Oore

In this paper, we propose a new compositional tool that will generate a musical outline of speech recorded/provided by the user for use as a musical building block in their compositions.

Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices

5 code implementations28 Dec 2019 Chandramouli Shama Sastry, Sageev Oore

We find that characterizing activity patterns by Gram matrices and identifying anomalies in gram matrix values can yield high OOD detection rates.

OOD Detection Out-of-Distribution Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.