
DataDriven Learning of Geometric Scattering Networks
Graph neural networks (GNNs) in general, and graph convolutional network...
read it

Visualizing structure and transitions in highdimensional biological data
The highdimensional data created by highthroughput technologies requir...
read it

Imagetoimage Mapping with Many Domains by Sparse Attribute Transfer
Unsupervised imagetoimage translation consists of learning a pair of m...
read it

Uncovering the Topology of TimeVarying fMRI Data using Cubical Persistence
Functional magnetic resonance imaging (fMRI) is a crucial technology for...
read it

Uncovering the Folding Landscape of RNA Secondary Structure with Deep Graph Embeddings
Biomolecular graph analysis has recently gained much attention in the em...
read it

Making Logic Learnable With Neural Networks
While neural networks are good at learning unspecified functions from tr...
read it

TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
It is increasingly common to encounter data from dynamic processes captu...
read it

Visualizing the PHATE of Neural Networks
Understanding why and how certain neural networks outperform others is k...
read it

Coarse Graining of Data via Inhomogeneous Diffusion Condensation
Big data often has emergent structure that exists at multiple levels of ...
read it

A Lipschitzconstrained anomaly discriminator framework
Anomaly detection is a problem of great interest in medicine, finance, a...
read it

TraVeLGAN: Imagetoimage Translation by Transformation Vector Learning
Interest in imagetoimage translation has grown substantially in recent...
read it

Compressed Diffusion
Diffusion maps are a commonly used kernelbased method for manifold lear...
read it

Finding Archetypal Spaces for Data Using Neural Networks
Archetypal analysis is a type of factor analysis where data is fit by a ...
read it

Generating and Aligning from Data Geometries with Generative Adversarial Networks
Unsupervised domain mapping has attracted substantial attention in recen...
read it

Graph Spectral Regularization for Neural Network Interpretability
Deep neural networks can learn meaningful representations of data. Howev...
read it

Manifold Alignment with Feature Correspondence
We propose a novel framework for combining datasets via alignment of the...
read it

GeometryBased Data Generation
Many generative models attempt to replicate the density of their input d...
read it

Modeling Dynamics with Deep TransitionLearning Networks
Markov processes, both classical and higher order, are often used to mod...
read it
Smita Krishnaswamy
verfied profile
Smita Krishnaswamy is an Assistant Professor in the department of Genetics at the Yale School of Medicine and Department of Computer Science in the Yale School of Applied Science and Engineering. She is also affiliated with the Yale Center for Biomedical Data Science, Yale Cancer Center, and Program in Applied Mathematics. Smita’s research focuses on developing unsupervised machine learning methods (especially graph signal processing and deeplearning) to denoise, impute, visualize and extract structure, patterns and relationships from big, high throughput, high dimensional biomedical data. Her methods have been applied variety of datasets from many systems including embryoid body differentiation, zebrafish development, the epithelialtomesenchymal transition in breast cancer, lung cancer immunotherapy, infectious disease data, gut microbiome data and patient data.