Search Results for author:
Found 48 papers, 15 papers with code
Iterative Flow Matching -- Path Correction and Gradual Refinement for Enhanced Generative Modeling
Generative models for image generation are now commonly used for a wide variety of applications, ranging from guided image generation for entertainment to solving inverse problems.
Inversion of Magnetic Data using Learned Dictionaries and Scale Space
In this study, we propose an approach that integrates variable dictionary learning and scale-space methods to address these challenges.
Multiscale Training of Convolutional Neural Networks
Convolutional Neural Networks (CNNs) are the backbone of many deep learning methods, but optimizing them remains computationally expensive.
DAWN-FM: Data-Aware and Noise-Informed Flow Matching for Solving Inverse Problems
Inverse problems, which involve estimating parameters from incomplete or noisy observations, arise in various fields such as medical imaging, geophysics, and signal processing.
Learning Regularization for Graph Inverse Problems
In recent years, Graph Neural Networks (GNNs) have been utilized for various applications ranging from drug discovery to network design and social networks.
Fully invertible hyperbolic neural networks for segmenting large-scale surface and sub-surface data
Examples in hyperspectral land-use classification, airborne geophysical surveying, and seismic imaging illustrate that we can input large data volumes in one chunk and do not need to work on small patches, use dimensionality reduction, or employ methods that classify a patch to a single central pixel.
Advection Augmented Convolutional Neural Networks
Many problems in physical sciences are characterized by the prediction of space-time sequences.
Deep Optimal Experimental Design for Parameter Estimation Problems
We show that the training of a network as a Likelihood Free Estimator can be used to significantly simplify the design process and circumvent the need for the computationally expensive bi-level optimization problem that is inherent in optimal experimental design for non-linear systems.
Graph Neural Reaction Diffusion Models
The integration of Graph Neural Networks (GNNs) and Neural Ordinary and Partial Differential Equations has been extensively studied in recent years.
Ranked #1 on
Node Classification
on Texas
Beyond Conventional Parametric Modeling: Data-Driven Framework for Estimation and Prediction of Time Activity Curves in Dynamic PET Imaging
Dynamic Positron Emission Tomography (dPET) imaging and Time-Activity Curve (TAC) analyses are essential for understanding and quantifying the biodistribution of radiopharmaceuticals over time and space.
Paired Autoencoders for Likelihood-free Estimation in Inverse Problems
We consider the solution of nonlinear inverse problems where the forward problem is a discretization of a partial differential equation.
Graph Neural Networks for Binary Programming
This paper investigates a link between Graph Neural Networks (GNNs) and Binary Programming (BP) problems, laying the groundwork for GNNs to approximate solutions for these computationally challenging problems.
An Over Complete Deep Learning Method for Inverse Problems
The novelty of the work proposed is that we jointly design and learn the embedding and the regularizer for the embedding vector.
On The Temporal Domain of Differential Equation Inspired Graph Neural Networks
Graph Neural Networks (GNNs) have demonstrated remarkable success in modeling complex relationships in graph-structured data.
Feature Transportation Improves Graph Neural Networks
Graph neural networks (GNNs) have shown remarkable success in learning representations for graph-structured data.
DRIP: Deep Regularizers for Inverse Problems
First, most techniques cannot guarantee that the solution fits the data at inference.
Semi-Automated Segmentation of Geoscientific Data Using Superpixels
Geological processes determine the distribution of resources such as critical minerals, water, and geothermal energy.
Every Node Counts: Improving the Training of Graph Neural Networks on Node Classification
In this paper, we propose novel objective terms for the training of GNNs for node classification, aiming to exploit all the available data and improve accuracy.
Neural DAEs: Constrained neural networks
This article investigates the effect of explicitly adding auxiliary algebraic trajectory information to neural networks for dynamical systems.
Estimating a potential without the agony of the partition function
In this paper we propose an alternative approach based on Maximum A-Posteriori (MAP) estimators, we name Maximum Recovery MAP (MR-MAP), to derive estimators that do not require the computation of the partition function, and reformulate the problem as an optimization problem.
pathGCN: Learning General Graph Spatial Operators from Paths
In the context of GCNs, differently from CNNs, a pre-determined spatial operator based on the graph Laplacian is often chosen, allowing only the point-wise operations to be learnt.
A-Optimal Active Learning
The first is based on a Bayesian interpretation of the semi-supervised learning problem with the graph Laplacian that is used for the prior distribution and the second is based on a frequentist approach, that updates the estimation of the bias term based on the recovery of the labels.
PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
Moreover, as we demonstrate using an extensive set of experiments, our PDE-motivated networks can generalize and be effective for various types of problems from different fields.
An Introduction to Deep Generative Modeling
Developing DGMs has become one of the most hotly researched fields in artificial intelligence in recent years.
Mimetic Neural Networks: A unified framework for Protein Design and Folding
Recent advancements in machine learning techniques for protein folding motivate better results in its inverse problem -- protein design.
Segmentation of Pulmonary Opacification in Chest CT Scans of COVID-19 Patients
In this work we provide open source models for the segmentation of patterns of pulmonary opacification on chest Computed Tomography (CT) scans which have been correlated with various stages and severities of infection.
Fully reversible neural networks for large-scale surface and sub-surface characterization via remote sensing
The large spatial/frequency scale of hyperspectral and airborne magnetic and gravitational data causes memory issues when using convolutional neural networks for (sub-) surface characterization.
Symmetric block-low-rank layers for fully reversible multilevel neural networks
Factors that limit the size of the input and output of a neural network include memory requirements for the network states/activations to compute gradients, as well as memory for the convolutional kernels or other weights.
LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks
In practice, the input data and the hidden features consist of a large number of channels, which in most CNNs are fully coupled by the convolution operators.
Fluid Flow Mass Transport for Generative Networks
Generative Adversarial Networks have been shown to be powerful in generating content.
Fully Hyperbolic Convolutional Neural Networks
However, their application to problems with high dimensional input and output, such as high-resolution image and video segmentation or 3D medical imaging, has been limited by various factors.
LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks
Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils.
Neural-networks for geophysicists and their application to seismic data interpretation
Neural-networks have seen a surge of interest for the interpretation of seismic images during the last few years.
IMEXnet: A Forward Stable Deep Neural Network
Deep convolutional neural networks have revolutionized many machine learning and computer vision tasks, however, some remaining key challenges limit their wider use.
AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
In this paper, we draw connections between recurrent networks and ordinary differential equations.
ADMM-SOFTMAX : An ADMM Approach for Multinomial Logistic Regression
Solution of the least-squares problem can be be accelerated by pre-computing a factorization or preconditioner, and the separability in the smooth, convex problem can be easily parallelized across examples.
Automatic classification of geologic units in seismic images using partially interpreted examples
Tests on seismic images and interpretation information from the Sea of Ireland show that we obtain high-quality predicted interpretations from a small number of large seismic images.
Multi-resolution neural networks for tracking seismic horizons from few training images
Our networks learn from a small number of large seismic images without creating patches.
GlymphVIS: Visualizing Glymphatic Transport Pathways Using Regularized Optimal Transport
The glymphatic system (GS) is a transit passage that facilitates brain metabolic waste removal and its dysfunction has been associated with neurodegenerative diseases such as Alzheimer's disease.
Never look back - A modified EnKF method and its application to the training of neural networks without back propagation
Further, we provide numerical examples that demonstrate the potential of our method for training deep neural networks.
Simultaneous shot inversion for nonuniform geometries using fast data interpolation
Stochastic optimization is key to efficient inversion in PDE-constrained optimization.
Deep Neural Networks Motivated by Partial Differential Equations
In the latter area, PDE-based approaches interpret image data as discretizations of multivariate functions and the output of image processing algorithms as solutions to certain PDEs.
Ranked #68 on
Image Classification
on STL-10
Multi-level Residual Networks from Dynamical Systems View
Deep residual networks (ResNets) and their variants are widely used in many computer vision applications and natural language processing tasks.
Reversible Architectures for Arbitrarily Deep Residual Neural Networks
In this work, we interpret deep residual networks as ordinary differential equations (ODEs), which have long been studied in mathematics and physics with rich theoretical and empirical success.
Ranked #48 on
Image Classification
on STL-10
A numerical method for efficient 3D inversions using Richards equation
Fluid flow in the vadose zone is governed by Richards equation; it is parameterized by hydraulic conductivity, which is a nonlinear function of pressure head.
Geophysics
Stable Architectures for Deep Neural Networks
While our new architectures restrict the solution space, several numerical experiments show their competitiveness with state-of-the-art networks.
Learning across scales - A multiscale method for Convolution Neural Networks
In this work we establish the relation between optimal control and training deep Convolution Neural Networks (CNNs).
jInv -- a flexible Julia package for PDE parameter estimation
Estimating parameters of Partial Differential Equations (PDEs) from noisy and indirect measurements often requires solving ill-posed inverse problems.
Mathematical Software
