no code implementations • 25 Jan 2023 • Sanjukta Krishnagopal, Luana Ruiz
We use graphons to define limit objects -- graphon NNs for GNNs, and graphon NTKs for GNTKs -- , and prove that, on a sequence of graphs, the GNTKs converge to the graphon NTK.
no code implementations • 10 Dec 2021 • Sanjukta Krishnagopal, Peter Latham
The grating is often low in contrast which makes the task relatively difficult, and the prior probability that the grating appears on the right is either 80% or 20%, in (unsignaled) blocks of about 50 trials.
no code implementations • 29 Sep 2021 • Sanjukta Krishnagopal, Keith Lohse, Robynne Braun
To demonstrate the utility of this approach, we analyzed data from the NINDS tPA trial using the Trajectory Profile Clustering (TPC) method to identify distinct stroke recovery patterns for 11 different neurological domains at 5 discrete time points.
1 code implementation • 2 Oct 2020 • Sanjukta Krishnagopal, Jacob Bedrossian
While variational autoencoders have been successful in several tasks, the use of conventional priors are limited in their ability to encode the underlying structure of input data.
1 code implementation • 29 May 2020 • Sanjukta Krishnagopal
Many diseases display heterogeneity in clinical features and their progression, indicative of the existence of disease subtypes.
1 code implementation • 18 Oct 2019 • Sanjukta Krishnagopal, Michelle Girvan, Edward Ott, Brian Hunt
Indeed, our method works well when the component frequency spectra are indistinguishable - a case where a Wiener filter performs essentially no separation.
1 code implementation • 12 Jun 2019 • Sanjukta Krishnagopal, Rainer Von Coelln, Lisa M. Shulman, Michelle Girvan
In summary, using PD as a model for chronic progressive diseases, we show that TPC leverages high-dimensional longitudinal datasets for subtype identification and early prediction of individual disease subtype.
Applications Dynamical Systems Biological Physics Data Analysis, Statistics and Probability
no code implementations • ICLR 2018 • Sanjukta Krishnagopal, Yiannis Aloimonos, Michelle Girvan
Thus, as opposed to training the entire high dimensional reservoir state, the reservoir only needs to train on these unique relationships, allowing the reservoir to perform well with very few training examples.