On Memorization in Probabilistic Deep Generative Models

1 code implementation • NeurIPS 2021 • Gerrit van den Burg, Chris Williams

Recent advances in deep generative models have led to impressive results in a variety of application domains.

Density Estimation Memorization

Unit-level surprise in neural networks

no code implementations • NeurIPS Workshop ICBINB 2021 • Cian Eastwood, Ian Mason, Chris Williams

To adapt to changes in real-world data distributions, neural networks must update their parameters.

Fast Holographic Deconvolution: a new technique for precision radio interferometry

2 code implementations • 7 Sep 2012 • Ian Sullivan, Miguel Morales, Bryna Hazelton, Wayne Arcus, David Barnes, Gianni Bernardi, Frank Briggs, Judd D. Bowman, John Bunton, Roger Cappallo, Brian Corey, Avinash Deshpande, Ludi deSouza, David Emrich, B. M. Gaensler, Robert Goeke, Lincoln Greenhill, David Herne, Jacqueline Hewitt, Melanie Johnston-Hollitt, David Kaplan, Justin Kasper, Barton Kincaid, Ronald Koenig, Eric Kratzenberg, Colin Lonsdale, Mervyn Lynch, Russell McWhirter, Daniel Mitchell, Edward Morgan, Divya Oberoi, Stephen Ord, Joseph Pathikulangara, Thiagaraj Prabu, Ron Remillard, Alan Rogers, Anish Roshi, Joseph Salah, Robert Sault, Udaya Shankar, K. Srivani, Jamie Stevens, Ravi Subrahmanyan, Steven Tingay, Randall Wayth, Mark Waterson, Rachel Webster, Alan Whitney, Andrew Williams, Chris Williams, Stuart Wyithe

We introduce the Fast Holographic Deconvolution method for analyzing interferometric radio data.

Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics