
Efficient Saliency Maps for Explainable AI
We describe an explainable AI saliency map method for use with deep conv...
read it

What and When to Look?: Temporal Span Proposal Network for Video Visual Relation Detection
Identifying relations between objects is central to understanding the sc...
read it

Attend and Decode: 4D fMRI Task State Decoding Using Attention Models
Functional magnetic resonance imaging (fMRI) is a neuroimaging modality ...
read it

Anomalous Instance Detection in Deep Learning: A Survey
Deep Learning (DL) is vulnerable to outofdistribution and adversarial ...
read it

Efficient, Interpretable Atomistic Graph Neural Network Representation for Angledependent Properties and its Application to Optical Spectroscopy Prediction
Graph neural networks (GNNs) are attractive for learning properties of a...
read it

Generative Counterfactual Introspection for Explainable Deep Learning
In this work, we propose an introspection technique for deep neural netw...
read it

On the Design of Blackbox Adversarial Examples by Leveraging Gradientfree Optimization and Operator Splitting Method
Robust machine learning is currently one of the most prominent topics wh...
read it

Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration
The hypothesis that subnetwork initializations (lottery) exist within t...
read it

Designing Accurate Emulators for Scientific Processes using CalibrationDriven Deep Models
Predictive models that accurately emulate complex scientific processes c...
read it

Function Preserving Projection for Scalable Exploration of HighDimensional Data
We present function preserving projections (FPP), a scalable linear proj...
read it

MixnMatch: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning
This paper studies the problem of posthoc calibration of machine learni...
read it

On Parallel Solution of Sparse Triangular Linear Systems in CUDA
The acceleration of sparse matrix computations on modern manycore proce...
read it

Improvements to context based selfsupervised learning
We develop a set of methods to improve on the results of selfsupervised...
read it

Autoencoder Node Saliency: Selecting Relevant Latent Representations
The autoencoder is an artificial neural network model that learns hidden...
read it

A Capacity Scaling Law for Artificial Neural Networks
By assuming an ideal neural network with gating functions handling the w...
read it

Optimizing Kernel Machines using Deep Learning
Building highly nonlinear and nonparametric models is central to sever...
read it

Robust Federated Learning Using ADMM in the Presence of Data Falsifying Byzantines
In this paper, we consider the problem of federated (or decentralized) l...
read it

A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning
We have created a large diverse set of cars from overhead images, which ...
read it

Learning Robust Representations for Computer Vision
Unsupervised learning techniques in computer vision often require learni...
read it

Bootstrapping Graph Convolutional Neural Networks for Autism Spectrum Disorder Classification
Using predictive models to identify patterns that can act as biomarkers ...
read it

A Spectral Approach for the Design of Experiments: Design, Analysis and Algorithms
This paper proposes a new approach to construct high quality spacefilli...
read it

Disentangling Space and Time in Video with Hierarchical Variational Autoencoders
There are many forms of feature information present in video data. Princ...
read it

A Selection of Giant Radio Sources from NVSS
Results of the application of pattern recognition techniques to the prob...
read it

Universal Collaboration Strategies for Signal Detection: A Sparse Learning Approach
This paper considers the problem of high dimensional signal detection in...
read it

RoleDynamics: Fast Mining of Large Dynamic Networks
To understand the structural dynamics of a largescale social, biologica...
read it

Contemporary machine learning: a guide for practitioners in the physical sciences
Machine learning is finding increasingly broad application in the physic...
read it

Conservative model reduction for finitevolume models
This work proposes a method for model reduction of finitevolume models ...
read it

Highorder Discretization of a Gyrokinetic Vlasov Model in Edge Plasma Geometry
We present a highorder spatial discretization of a continuum gyrokineti...
read it

A DataCentric View on Computational Complexity: P = NP
P = NP SAT ∈ P. We propose this to be true because the satisfiability ...
read it

Kinetic Simulation of Collisional Magnetized Plasmas with SemiImplicit Time Integration
Plasmas with varying collisionalities occur in many applications, such a...
read it

Spacetime leastsquares PetrovGalerkin projection for nonlinear model reduction
This work proposes a spacetime leastsquares PetrovGalerkin (STLSPG) ...
read it

Principle of Conservation of Computational Complexity
In this manuscript, we derive the principle of conservation of computati...
read it

Modeling sepsis progression using hidden Markov models
Characterizing a patient's progression through stages of sepsis is criti...
read it

Salable BreadthFirst Search on a GPU Cluster
On a GPU cluster, the ratio of high computing power to communication ban...
read it

Highdimensional Stochastic Inversion via Adjoint Models and Machine Learning
Performing stochastic inversion on a computationally expensive forward s...
read it

On LargeScale Graph Generation with Validation of Diverse Triangle Statistics at Edges and Vertices
Researchers developing implementations of distributed graph analytic alg...
read it

Scalable BreadthFirst Search on a GPU Cluster
On a GPU cluster, the ratio of high computing power to communication ban...
read it

An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks
Solving inverse problems continues to be a challenge in a wide array of ...
read it

TTHRESH: Tensor Compression for Multidimensional Visual Data
Memory and network bandwidth are decisive bottlenecks when handling high...
read it

Triplet Network with Attention for Speaker Diarization
In automatic speech processing systems, speaker diarization is a crucial...
read it

FlipTracker: Understanding Natural Error Resilience in HPC Applications
As highperformance computing systems scale in size and computational po...
read it

Controlled Random Search Improves Sample Mining and HyperParameter Optimization
A common challenge in machine learning and related fields is the need to...
read it

Low synchronization GMRES algorithms
Communicationavoiding and pipelined variants of Krylov solvers are crit...
read it

A Practical Approach to Sizing Neural Networks
Memorization is worstcase generalization. Based on MacKay's information...
read it

Statistical Treatment of Inverse Problems Constrained by Differential EquationsBased Models with Stochastic Terms
This paper introduces a statistical treatment of inverse problems constr...
read it

Designing an Effective Metric Learning Pipeline for Speaker Diarization
Stateoftheart speaker diarization systems utilize knowledge from exte...
read it

Improving Robustness of Attention Models on Graphs
Machine learning models that can exploit the inherent structure in data ...
read it

Unsupervised Dimension Selection using a Blue Noise Spectrum
Unsupervised dimension selection is an important problem that seeks to r...
read it

Understanding Deep Neural Networks through Input Uncertainties
Techniques for understanding the functioning of complex machine learning...
read it

Universal Hardlabel BlackBox Perturbations: Breaking SecurityThroughObscurity Defenses
We study the problem of finding a universal (imageagnostic) perturbatio...
read it
Lawrence Livermore National Laboratory
Lawrence Livermore National Laboratory is a federal research facility in Livermore, California, United States, founded by the University of California, Berkeley in 1952.