
Lifelong Learning with Sketched Structural Regularization
Preventing catastrophic forgetting while continually learning new tasks ...
read it

Set Representation Learning with Generalized SlicedWasserstein Embeddings
An increasing number of machine learning tasks deal with learning repres...
read it

Wasserstein Embedding for Graph Learning
We present Wasserstein Embedding for Graph Learning (WEGL), a novel and ...
read it

Radon cumulative distribution transform subspace modeling for image classification
We present a new supervised image classification method for problems whe...
read it

Statistical and Topological Properties of Sliced Probability Divergences
The idea of slicing divergences has been proven to be successful when co...
read it

Generalized Sliced Distances for Probability Distributions
Probability metrics have become an indispensable part of modern statisti...
read it

Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture
This paper introduces the modulated Hebbian plus Q network architecture ...
read it

Learning a DomainInvariant Embedding for Unsupervised Domain Adaptation Using ClassConditioned Distribution Alignment
We address the problem of unsupervised domain adaptation (UDA) by learni...
read it

Neural Networks, Hypersurfaces, and Radon Transforms
Connections between integration along hypersufaces, Radon transforms, an...
read it

Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs
The unprecedented success of deep neural networks in various application...
read it

Generative Continual Concept Learning
After learning a concept, humans are also able to continually generalize...
read it

DivideandConquer Adversarial Detection
The vulnerabilities of deep neural networks against adversarial examples...
read it

On Sampling Random Features From Empirical Leverage Scores: Implementation and Theoretical Guarantees
Random features provide a practical framework for largescale kernel app...
read it

Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay
Despite huge success, deep networks are unable to learn effectively in s...
read it

Using World Models for PseudoRehearsal in Continual Learning
The utility of learning a dynamics/world model of the environment in rei...
read it

AttentionBased StructuralPlasticity
Catastrophic forgetting/interference is a critical problem for lifelong ...
read it

Neuromodulated GoalDriven Perception in Uncertain Domains
In uncertain domains, the goals are often unknown and need to be predict...
read it

Generalized Sliced Wasserstein Distances
The Wasserstein distance and its variations, e.g., the slicedWasserstei...
read it

Discovering Molecular Functional Groups Using Graph Convolutional Neural Networks
Functional groups (FGs) serve as a foundation for analyzing chemical pro...
read it

SlicedWasserstein Autoencoder: An Embarrassingly Simple Generative Model
In this paper we study generative modeling via autoencoders while using ...
read it

Image to Image Translation for Domain Adaptation
We propose a general framework for unsupervised domain adaptation, which...
read it

Sliced Wasserstein Distance for Learning Gaussian Mixture Models
Gaussian mixture models (GMM) are powerful parametric tools with many ap...
read it

Joint Dictionaries for ZeroShot Learning
A classic approach toward zeroshot learning (ZSL) is to map the input d...
read it

Discovery and visualization of structural biomarkers from MRI using transportbased morphometry
Disease in the brain is often associated with subtle, spatially diffuse,...
read it

A Transportation L^p Distance for Signal Analysis
Transport based distances, such as the Wasserstein distance and earth mo...
read it

Transportbased analysis, modeling, and learning from signal and data distributions
Transportbased techniques for signal and data analysis have received in...
read it

The Radon cumulative distribution transform and its application to image classification
Invertible image representation methods (transforms) are routinely emplo...
read it

Sliced Wasserstein Kernels for Probability Distributions
Optimal transport distances, otherwise known as Wasserstein distances, h...
read it

The Cumulative Distribution Transform and Linear Pattern Classification
Discriminating data classes emanating from sensors is an important probl...
read it
Soheil Kolouri
verfied profile
Research Scientist at HRL Laboratories, LLC