SEARCH · Engineering Papers

Results for “sparse neural network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Spike-and-Slab Shrinkage Priors for Structurally Sparse Bayesian Neural Networks

Network complexity and computational efficiency have become increasingly significant aspects of deep learning. Sparse deep learning addresses these challenges by recovering a sparse representation of the underlying target function by reducing heavily overparameterized deep neural networks. Specifically, deep neural architectures compressed via structured sparsity (e.g., node sparsity) provide low-latency inference, higher data throughput, and reduced energy consumption. In this article, we explore two well-established shrinkage techniques, Lasso and Horseshoe, for model compression in Bayesian neural networks (BNNs). To this end, we propose structurally sparse BNNs, which systematically prune excessive nodes with the following: 1) spike-and-slab group Lasso (SS-GL) and 2) SS group Horseshoe (SS-GHS) priors, and develop computationally tractable variational inference, including continuous relaxation of Bernoulli variables. We establish the contraction rates of the variational posterior of our proposed models as a function of the network topology, layerwise node cardinalities, and bounds on the network weights. Furthermore, we empirically demonstrate the competitive performance of our models compared with the baseline models in prediction accuracy, model compression, and inference latency.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Distributed-Memory Sparse Deep Neural Network Inference Using Global Arrays

Partitioned Global Address Space (PGAS) models exhibit tremendous promise in developing efficient and productive distributed-memory parallel applications. They have been used extensively in scientific computations due to conveniently offering a ``shared-memory''-like model and convenient interfaces that separate communication with synchronization. Traditionally, PGAS communication models have been applied to dense/contiguously distributed data, but most modern applications depict varied levels of sparsity. Existing PGAS models require certain adaptations to support distributed sparse computations, since associated computations often require matrix arithmetic, in addition to data movement. The Global Arrays toolkit from Pacific Northwest National Laboratory (PNNL) is one of the earliest PGAS models to combine one-sided data communication and distributed matrix operations and is still used in the popular NWChem quantum chemistry suite. Recently, we have expanded the Global Arrays toolkit to support common sparse operations, like sparse matrix-dense matrix multiplies (SpMM), sparse matrix-sparse matrix multiplication (SpGEMM) and Sampled Dense-Dense Matrix Multiplication (SDDMM). As it turns out, these operations are the bedrock of sparse Deep Learning (DL); sparse deep neural networks and Graph Neural Networks (GNNs) have gained increasing attention recently in achieving speedups on training and inference with reduced memory footprints. Unlike scientific applications in High Performance Computing (HPC), modern (distributed-memory capable) DL toolkits often rely on non-standardized and closed-source vendor software optimizations, creating challenges in software-hardware co-design at scale. Our goal is to support a variety of distributed-memory sparse matrix operations and helper functions in the newly created Sparse Global Arrays (SGA), such that it is possible to build portable and productive Machine Learning scenarios for algorithm/software and hardware codesign purposes. Contemporary data-parallel schemes for training/inference are undergoing a major overhaul since model replication limits scalability and causes resource inefficiencies. As such, we have adopted tensor parallelism in decomposing the model and inputs, to mitigate memory issues. Current implementation is built on top of MPI and uses CPUs to maximize the portability across the platforms.

Distributed computing, machine learning↗

NASA NTRS2002

Prediction of Aerodynamic Coefficient using Genetic Algorithm Optimized Neural Network for Sparse Data

Wind tunnels use scale models to characterize aerodynamic coefficients, Wind tunnel testing can be slow and costly due to high personnel overhead and intensive power utilization. Although manual curve fitting can be done, it is highly efficient to use a neural network to define the complex relationship between variables. Numerical simulation of complex vehicles on the wide range of conditions required for flight simulation requires static and dynamic data. Static data at low Mach numbers and angles of attack may be obtained with simpler Euler codes. Static data of stalled vehicles where zones of flow separation are usually present at higher angles of attack require Navier-Stokes simulations which are costly due to the large processing time required to attain convergence. Preliminary dynamic data may be obtained with simpler methods based on correlations and vortex methods; however, accurate prediction of the dynamic coefficients requires complex and costly numerical simulations. A reliable and fast method of predicting complex aerodynamic coefficients for flight simulation I'S presented using a neural network. The training data for the neural network are derived from numerical simulations and wind-tunnel experiments. The aerodynamic coefficients are modeled as functions of the flow characteristics and the control surfaces of the vehicle. The basic coefficients of lift, drag and pitching moment are expressed as functions of angles of attack and Mach number. The modeled and training aerodynamic coefficients show good agreement. This method shows excellent potential for rapid development of aerodynamic models for flight simulation. Genetic Algorithms (GA) are used to optimize a previously built Artificial Neural Network (ANN) that reliably predicts aerodynamic coefficients. Results indicate that the GA provided an efficient method of optimizing the ANN model to predict aerodynamic coefficients. The reliability of the ANN using the GA includes prediction of aerodynamic coefficients to an accuracy of 110% . In our problem, we would like to get an optimized neural network architecture and minimum data set. This has been accomplished within 500 training cycles of a neural network. After removing training pairs (outliers), the GA has produced much better results. The neural network constructed is a feed forward neural network with a back propagation learning mechanism. The main goal has been to free the network design process from constraints of human biases, and to discover better forms of neural network architectures. The automation of the network architecture search by genetic algorithms seems to have been the best way to achieve this goal.

Rajkumar, T.↗

NASA NTRS2002

Prediction of Aerodynamic Coefficients using Neural Networks for Sparse Data

Basic aerodynamic coefficients are modeled as functions of angles of attack and sideslip with vehicle lateral symmetry and compressibility effects. Most of the aerodynamic parameters can be well-fitted using polynomial functions. In this paper a fast, reliable way of predicting aerodynamic coefficients is produced using a neural network. The training data for the neural network is derived from wind tunnel test and numerical simulations. The coefficients of lift, drag, pitching moment are expressed as a function of alpha (angle of attack) and Mach number. The results produced from preliminary neural network analysis are very good.

Rajkumar, T.↗

NASA NTRS1990

An efficient optical architecture for sparsely connected neural networks

An architecture for general-purpose optical neural network processor is presented in which the interconnections and weights are formed by directing coherent beams holographically, thereby making use of the space-bandwidth products of the recording medium for sparsely interconnected networks more efficiently that the commonly used vector-matrix multiplier, since all of the hologram area is in use. An investigation is made of the use of computer-generated holograms recorded on such updatable media as thermoplastic materials, in order to define the interconnections and weights of a neural network processor; attention is given to limits on interconnection densities, diffraction efficiencies, and weighing accuracies possible with such an updatable thin film holographic device.

Hine, Butler P., III↗

DOE OSTI2025

An adaptive and stability-promoting layerwise training approach for sparse deep neural network architecture

This work presents a two-stage adaptive framework for progressively developing deep neural network (DNN) architectures that generalize well for a given training data set. In the first stage, a layerwise training approach is adopted where a new layer is added each time and trained independently by freezing parameters in the previous layers. We impose desirable structures on the DNN by employing manifold regularization, sparsity regularization, and physics-informed terms. We introduce a ε – δ – stability-promoting concept as a desirable property for a learning algorithm and show that employing manifold regularization yields a ε – δ stability-promoting algorithm. Further, we also derive the necessary conditions for the trainability of a newly added layer and investigate the training saturation problem. In the second stage of the algorithm (post-processing), a sequence of shallow networks is employed to extract information from the residual produced in the first stage, thereby improving the prediction accuracy. Numerical investigations on prototype regression and classification problems demonstrate that the proposed approach can outperform fully connected DNNs of the same size. Moreover, by equipping the physics-informed neural network (PINN) with the proposed adaptive architecture strategy to solve partial differential equations, we numerically show that adaptive PINNs not only are superior to standard PINNs but also produce interpretable hidden layers with provable stability. As a result, we also apply our architecture design strategy to solve inverse problems governed by elliptic partial differential equations.

42 ENGINEERING↗

NASA NTRS1986

Comparison between sparsely distributed memory and Hopfield-type neural network models

The Sparsely Distributed Memory (SDM) model (Kanerva, 1984) is compared to Hopfield-type neural-network models. A mathematical framework for comparing the two is developed, and the capacity of each model is investigated. The capacity of the SDM can be increased independently of the dimension of the stored vectors, whereas the Hopfield capacity is limited to a fraction of this dimension. However, the total number of stored bits per matrix element is the same in the two models, as well as for extended models with higher order interactions. The models are also compared in their ability to store sequences of patterns. The SDM is extended to include time delays so that contextual information can be used to cover sequences. Finally, it is shown how a generalization of the SDM allows storage of correlated input pattern vectors.

Keeler, James D.↗

DOE OSTI2024

Predicting Missing Regions in Charged Particle Tracks Using a Sparse 3D Convolutional Neural Network

The 2x2 Demonstrator is a prototype detector for the Deep Underground Neutrino Experiment (DUNE)'s Near Detector. Both the 2x2 Demonstrator and the Near Detector itself will have inactive regions wherein there is no sensitivity to charge deposition and light signals that arise from charged particle interactions with liquid argon. In the 2x2, these inactive regions are positioned in-between the active detector modules, which introduces the challenge of inferring what charge signals ought to look like in these regions. This study explores the use of a Sparse 3D Convolutional Neural Network (ConvNet) to infer missing regions in charged particle tracks. Hits corresponding to energy depositions are voxelized into a three-dimensional (3D) grid for each track. Inactive regions within the tracks are replaced with a dense, rectangular 3D grid of voxels, ensuring consistent step sizes in X, Y, and Z directions. Voxels in these dense regions are initialized with an energy value of -1, indicating nonphysical energy or charge. The model is trained to predict which voxels should activate as part of the track and which should not, with the goal of eventually inferring the missing charge or energy values in these voxels. Results indicate that the model accurately predicts track voxels within ±1 unit in X, Y, or Z directions and effectively identifies non-track voxels, despite some overprediction. The approach shows promise in prediction of missing track regions with some accuracy.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

Predicting Missing Regions in Charged Particle Tracks Using a Sparse 3D Convolutional Neural Network

The 2x2 Demonstrator is a prototype detector for the Deep Underground Neutrino Experiment (DUNE)'s Near Detector. Both the 2x2 Demonstrator and the Near Detector itself will have inactive regions wherein there is no sensitivity to charge deposition and light signals that arise from charged particle interactions with liquid argon. In the 2x2, these inactive regions are positioned in-between the active detector modules, which introduces the challenge of inferring what charge signals ought to look like in these regions. This study explores the use of a Sparse 3D Convolutional Neural Network (ConvNet) to infer missing regions in charged particle tracks. Hits corresponding to energy depositions are voxelized into a three-dimensional (3D) grid for each track. Inactive regions within the tracks are replaced with a dense, rectangular 3D grid of voxels, ensuring consistent step sizes in X, Y, and Z directions. Voxels in these dense regions are initialized with an energy value of -1, indicating nonphysical energy or charge. The model is trained to predict which voxels should activate as part of the track and which should not, with the goal of eventually inferring the missing charge or energy values in these voxels. Results indicate that the model accurately predicts track voxels within 1 unit in X, Y, or Z directions and effectively identifies non-track voxels, despite some overprediction. The approach shows promise in prediction of missing track regions with some accuracy.

Utaegbulam, Hilary↗

DOE OSTI2024

Predicting Missing Regions in Charged Particle Tracks Using a Sparse 3D Convolutional Neural Network

The 2x2 Demonstrator is a prototype of ND-LAr, the liquid argon time-projection chamber of the Deep Underground Neutrino Experiment’s Near Detector complex. Both the 2x2 Demonstrator and ND-LAr are modular detectors that will have pixelated charge readouts and inactive regions wherein there is no sensitivity to charge deposition and light signals that arise from charged particle interactions with liquid argon. In the 2x2, these inactive regions are located in between the active detector modules, which introduces the challenge of inferring what charge signals ought to look like in these regions. This study explores the use of a Sparse 3D Convolutional Neural Network (ConvNet) to infer missing regions in charged particle tracks. Hits corresponding to energy depositions are voxelized into a three-dimensional grid for each track. Voxels that fall into predefined inactive regions are removed to simulate the lack of detector output. The model is trained to infer the topology of the missing track voxels, with the ultimate goal of inferring the missing charge or energy values in these voxels as well. Results indicate that this approach shows promise in prediction of missing track regions with some accuracy.

Utaegbulam, Hilary↗

NASA NTRS1989

Learning to read aloud: A neural network approach using sparse distributed memory

An attempt to solve a problem of text-to-phoneme mapping is described which does not appear amenable to solution by use of standard algorithmic procedures. Experiments based on a model of distributed processing are also described. This model (sparse distributed memory (SDM)) can be used in an iterative supervised learning mode to solve the problem. Additional improvements aimed at obtaining better performance are suggested.

Joglekar, Umesh Dwarkanath↗

DOE OSTI2025

Echo state network for coarsening dynamics of charge density waves

An echo state network (ESN) is a type of reservoir computer that uses a recurrent neural network with a sparsely connected hidden layer. Compared with other recurrent neural networks, one great advantage of ESN is the simplicity of its training process. Yet, despite the seemingly restricted learnable parameters, ESN has been shown to successfully capture the spatial-temporal dynamics of complex patterns. Here we build an ESN to model the coarsening dynamics of charge-density waves (CDWs) in a semiclassical Holstein model, which exhibits a checkerboard electron density modulation at half-filling stabilized by a commensurate lattice distortion. The inputs to the ESN are local CDW order parameters in a finite neighborhood centered around a given site, while the output is the predicted CDW order of the center site at the next time step. Special care is taken in the design of couplings between hidden layer and input nodes to ensure lattice symmetries are properly incorporated into the ESN model. Since the model predictions depend only on CDW configurations of a finite domain, the ESN is scalable and transferrable in the sense that a model trained on dataset from a small system can be directly applied to dynamical simulations on larger lattices. Furthermore, our work opens avenues for efficient dynamical modeling of pattern formations in functional electron materials.

2-dimensional systems↗

DOE OSTI2024

ReLU, Sparseness, and the Encoding of Optic Flow in Neural Networks

Accurate self-motion estimation is critical for various navigational tasks in mobile robotics. Optic flow provides a means to estimate self-motion using a camera sensor and is particularly valuable in GPS- and radio-denied environments. The present study investigates the influence of different activation functions—ReLU, leaky ReLU, GELU, and Mish—on the accuracy, robustness, and encoding properties of convolutional neural networks (CNNs) and multi-layer perceptrons (MLPs) trained to estimate self-motion from optic flow. Our results demonstrate that networks with ReLU and leaky ReLU activation functions not only achieved superior accuracy in self-motion estimation from novel optic flow patterns but also exhibited greater robustness under challenging conditions. The advantages offered by ReLU and leaky ReLU may stem from their ability to induce sparser representations than GELU and Mish do. Our work characterizes the encoding of optic flow in neural networks and highlights how the sparseness induced by ReLU may enhance robust and accurate self-motion estimation from optic flow.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Machine Learning for DUNE Supernova Trigger

One of the major scientific goals of the Deep Underground Neutrino Experiment (DUNE) is to detect and measure the neutrino flux originating from galactic core-collapse supernovae. These neutrinos provide an opportunity to study the end of life evolution of massive stars, and reveal information about the structure of core-collapse that is not visible in observations of the electromagnetic spectrum. Because of the rarity of these events, it is crucial that DUNE is able to detect supernova neutrino interactions when they occur. However, this will require sifting through a large quantity of data, motivating the development of a trigger algorithm to identify significant events and discard irrelevant data. Machine learning provides a potential approach to building this trigger. This project generates ADC and ground truth images of simulated neutrino interactions in a LArTPC detector to be used for machine learning, and uses them to train a sparse Convolutional Neural Network (C NN). The performance of this model when applied to the task of pixel classification based on interaction type is examined. This project found that the sparse CNN approach has the potential to have high accuracy in pixel classification, meaning it may be highly relevant to the development of a supernova neutrino trigger for the DUNE far detector.

Damish, S.↗

DOE OSTI2024

Muon Neutrino Reconstruction at ICARUS with Machine Learning

The ICARUS T600 LArTPC detector successfully ran for three years at the underground LNGS laboratories, providing a first sensitive search for LSND-like anomalous electron neutrino appearance in the CNGS beam. After a significant overhauling at CERN, the T600 detector has been placed in its experimental hall at Fermilab, fully commissioned, and the first events observed with full detector readout. Regular data-taking began in May 2021 with neutrinos from the Booster Neutrino Beam (BNB) and neutrinos six degrees off-axis from the Neutrinos at the Main Injector (NuMI). Modern developments in machine learning have allowed for the development of an end-to-end machine learning-based event reconstruction for ICARUS data. This reconstruction folds in 3D voxel-level feature extraction using sparse convolutional neural networks and particle clustering using graph neural networks to produce outputs suitable for physics analyses. This poster will summarize the performance of a high-purity and high-efficiency end-to-end machine learning-based selection of muon neutrinos from the BNB and highlight studies of electromagnetic shower reconstruction from a neutral pion selection.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

A First Search for Argon-Bound Neutron-Antineutron Oscillation using the MicroBooNE LArTPC

The use of Liquid Argon Time Projection Chambers (LArTPCs) as a detector technology in neutrino experiments has grown considerably over the past two decades. The excellent spatial and calorimetric resolution offered by LArTPCs enable precise neutrino oscillation measurements as well as beyond-Standard Model searches. One such search, which is the focus of this note, is the search for nucleus-bound neutron-antineutron (n ₋ n̄) oscillation. The n ₋ n̄ oscillation process is a baryon number violating process that produces a unique, star-like topology as a result of multiple final state pions. This unique signature is a key feature that may be used to search for this signal process. This note describes a machine learning-based analysis of MicroBooNE data, making use of a sparse convolutional neural network to search for n ₋ n̄ oscillation-like signals in MicroBooNE. While the future DUNE LArTPC can search for this signature with high sensitivity, existing MicroBooNE data can be used to demonstrate and validate methodologies that can be used as part of the DUNE search. This document presents the first-ever search for n ₋ n̄ oscillation in a LArTPC, using MicroBooNE off-beam data (data collected when the neutrino beam was not running).

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

A first search for argon-bound neutron-antineutron oscillation using the MicroBooNE LArTPC

The use of Liquid Argon Time Projection Chambers (LArTPCs) as a detector technology in neutrino experiments has grown considerably over the past two decades. The excellent spatial and calorimetric resolution offered by LArTPCs enable precise neutrino oscillation measurements as well as beyond-Standard Model searches. One such search, which is the focus of this note, is the search for nucleus-bound neutron-antineutron (n – n̄) oscillation. The n – n̄ oscillation process is a baryon number violating process that produces a unique, star-like topology as a result of multiple final state pions. This unique signature is a key feature that may be used to search for this signal process. This note describes a machine learning-based analysis of MicroBooNE data, making use of a sparse convolutional neural network to search for n – n̄ oscillation-like signals in MicroBooNE. While the future DUNE LArTPC can search for this signature with high sensitivity, existing MicroBooNE data can be used to demonstrate and validate methodologies that can be used as part of the DUNE search. This document presents the first-ever search for n – n̄ oscillation in a LArTPC, using MicroBooNE off-beam data (data collected when the neutrino beam was not running).

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2025

Explainable and Differentiable Reinforcement Learning for Multi-objective Optimization in Particle Accelerators

Operating particle accelerators involves optimizing multiple goals simultaneously, which can be challenging due to trade-offs among objectives. While evolutionary algorithms like the genetic algorithm (GA) have been used for various Multi-Objective Optimization (MOO) tasks, they are not inherently suited for complex control problems. This talk highlights two variations of Reinforcement Learning (RL) for concurrently optimizing heat load and trip rates at the Continuous Electron Beam Accelerator Facility (CEBAF). The problem involves strict constraints on individual states, actions, and overall energy requirements of the beam. First, this talk highlights how differentiability can be harnessed through a Deep Differentiable Reinforcement Learning (DDRL) approach to address MOO issues within particle accelerators. We examine the DDRL method alongside Model Free Reinforcement Learning (MFRL), GA, and Bayesian Optimization (BO). The performance of these methods is assessed by generating a Pareto-front for two objectives. Our findings indicate that DDRL excels in handling high-dimensional problems more effectively than MFRL, BO, and GA. Next, we will show integration of explainable physics-based constraints into RL algorithms to enhance trans- parency and trust in decision-making processes by enabling users to verify that agents adhere to established physical principles. This surrogate function can be modeled using neural networks or sparse dictionary mod- els. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment provided but the surrogate model. In addi- tion, we find that the introduction of a mathematical functional dictionary based surrogate model enables our reinforcement learning algorithms to reliably converge for difficult high-dimensional accelerator controls environments.

Rajput, Kishansingh [Thomas Jefferson National Acc↗