Search Results for author:
Found 21 papers, 12 papers with code
Operator Learning Meets Numerical Analysis: Improving Neural Networks through Iterative Methods
Deep neural networks, despite their success in numerous applications, often function without established theoretical foundations.
Continuous Spatiotemporal Transformers
Modeling spatiotemporal dynamical systems is a fundamental challenge in machine learning.
FIMP: Foundation Model-Informed Message Passing for Graph Neural Networks
Foundation models have revolutionized the landscape of Deep Learning (DL), serving as a versatile platform which can be adapted to a wide range of downstream tasks.
Neural Integral Equations
In this paper, we introduce Neural Integral Equations (NIE), a method that learns an unknown integral operator from data through an IE solver.
Neural Integro-Differential Equations
Further, we show that NIDE can decompose dynamics into their Markovian and non-Markovian constituents via the learned integral operator, which we test on fMRI brain activity recordings of people on ketamine.
Permutation invariant networks to learn Wasserstein metrics
In this work, we use a permutation invariant network to map samples from probability measures into a low-dimensional space such that the Euclidean distance between the encoded samples reflects the Wasserstein distance between probability measures.
Self-supervised edge features for improved Graph Neural Network training
In recent years, there has been a lot of work incorporating edge features along with node features for prediction tasks.
Gaining Insight into SARS-CoV-2 Infection and COVID-19 Severity Using Self-supervised Edge Features and Graph Neural Networks
A molecular and cellular understanding of how SARS-CoV-2 variably infects and causes severe COVID-19 remains a bottleneck in developing interventions to end the pandemic.
Explainable Artificial Intelligence (XAI)
General Classification
+3
Learning Potentials of Quantum Systems using Deep Neural Networks
Attempts to apply Neural Networks (NN) to a wide range of research problems have been ubiquitous and plentiful in recent literature.
Learning aligned embeddings for semi-supervised word translation using Maximum Mean Discrepancy
Word translation is an integral part of language translation.
Disease State Prediction From Single-Cell Data Using Graph Attention Networks
To the best of our knowledge, this is the first effort to use graph attention, and deep learning in general, to predict disease state from single-cell data.
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
To address this issue, we establish a link between continuous normalizing flows and dynamic optimal transport, that allows us to model the expected paths of points over time.
Beyond GANs: Transforming without a Target Distribution
While generative neural networks can learn to transform a specific input dataset into a specific target dataset, they require having just such a paired set of input/output datasets.
Coarse Graining of Data via Inhomogeneous Diffusion Condensation
Here, we consider multiple levels of abstraction via a multiresolution geometry of data points at different granularities.
Graph Spectral Regularization For Neural Network Interpretability
First, we show a synthetic example that the graph-structured layer can reveal topological features of the data.
Enhancing experimental signals in single-cell RNA-sequencing data using graph signal processing
Single-cell RNA-sequencing (scRNA-seq) is a powerful tool for analyzing biological systems.
Compressed Diffusion
Diffusion maps are a commonly used kernel-based method for manifold learning, which can reveal intrinsic structures in data and embed them in low dimensions.
Finding Archetypal Spaces Using Neural Networks
Here, we propose a reformulation of the problem such that the goal is to learn a non-linear transformation of the data into a latent archetypal space.
Interpretable Neuron Structuring with Graph Spectral Regularization
Taking inspiration from spatial organization and localization of neuron activations in biological networks, we use a graph Laplacian penalty to structure the activations within a layer.
Modeling Dynamics of Biological Systems with Deep Generative Neural Networks
DyMoN is well-suited to the idiosyncrasies of biological data, including noise, sparsity, and the lack of longitudinal measurements in many types of systems.
Modeling Global Dynamics from Local Snapshots with Deep Generative Neural Networks
In order to model the dynamics of such systems given snapshot data, or local transitions, we present a deep neural network framework we call Dynamics Modeling Network or DyMoN.
