Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “NEURAL NETWORKS”

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.

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

At least 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

Incorporation of varying types of temporal data in a neural network

Most neural network models do not specifically deal with temporal data. Handling of these variables is complicated by the different uses to which temporal data are put, depending on the application. Even within the same application, temporal variables are often used in a number of different ways. In this paper, types of temporal data are discussed, along with their implications for approximate reasoning. Methods for integrating approximate temporal reasoning into existing neural network structures are presented. These methods are illustrated in a medical application for diagnosis of graft-versus-host disease which requires the use of several types of temporal data.

Cohen, M. E.↗
DOE OSTI2020

Generic, Sparse Tensor Core for Neural Networks

Sparse neural network attracts more attention for model compression, fast execution, and power reduction. The state-of-the-art designed sparse tensor core for structured and static sparsity, which did not support well for generic or dynamic sparsity. We design a sparse tensor core to support generic sparsity pruning with a novel hybrid and blocked sparse matrix storage format, HB-ELL, which saves computation and storage while keeping the most significant elements, as well as supporting dynamic sparsity for data flow in neural networks. We achieve better performance with preliminary results than the state-of- the-art on an NVIDIA GPU simulator.

Wu, Xiaolong↗
NASA NTRS1993

Acoustic target detection and classification using neural networks

A neural network approach to the classification of acoustic emissions of ground vehicles and helicopters is demonstrated. Data collected during the Joint Acoustic Propagation Experiment conducted in July of l991 at White Sands Missile Range, New Mexico was used to train a classifier to distinguish between the spectrums of a UH-1, M60, M1 and M114. An output node was also included that would recognize background (i.e. no target) data. Analysis revealed specific hidden nodes responding to the features input into the classifier. Initial results using the neural network were encouraging with high correct identification rates accompanied by high levels of confidence.

Robertson, James A.↗
DOE OSTI2021

A systematic approach to generating accurate neural network potentials: the case of carbon

Abstract Availability of affordable and widely applicable interatomic potentials is the key needed to unlock the riches of modern materials modeling. Artificial neural network-based approaches for generating potentials are promising; however, neural network training requires large amounts of data, sampled adequately from an often unknown potential energy surface. Here we propose a self-consistent approach that is based on crystal structure prediction formalism and is guided by unsupervised data analysis, to construct an accurate, inexpensive, and transferable artificial neural network potential. Using this approach, we construct an interatomic potential for carbon and demonstrate its ability to reproduce first principles results on elastic and vibrational properties for diamond, graphite, and graphene, as well as energy ordering and structural properties of a wide range of crystalline and amorphous phases.

Chemistry↗
DOE OSTI2023

Architecture-Preserving Provable Repair of Deep Neural Networks

Deep neural networks (DNNs) are becoming increasingly important components of software, and are considered the state-of-the-art solution for a number of problems, such as image recognition. However, DNNs are far from infallible, and incorrect behavior of DNNs can have disastrous real-world consequences. This paper addresses the problem of architecture-preserving V-polytope provable repair of DNNs. A V-polytope defines a convex bounded polytope using its vertex representation. V-polytope provable repair guarantees that the repaired DNN satisfies the given specification on the infinite set of points in the given V-polytope. An architecture-preserving repair only modifies the parameters of the DNN, without modifying its architecture. The repair has the flexibility to modify multiple layers of the DNN, and runs in polynomial time. It supports DNNs with activation functions that have some linear pieces, as well as fully-connected, convolutional, pooling and residual layers. To the best our knowledge, this is the first provable repair approach that has all of these features. We implement our approach in a tool called APRNN. Using MNIST, ImageNet, and ACAS Xu DNNs, we show that it has better efficiency, scalability, and generalization compared to PRDNN and REASSURE, prior provable repair methods that are not architecture preserving.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1993

Parallel Consensual Neural Networks

A new neural network architecture is proposed and applied in classification of remote sensing/geographic data from multiple sources. The new architecture is called the parallel consensual neural network and its relation to hierarchical and ensemble neural networks is discussed. The parallel consensual neural network architecture is based on statistical consensus theory. The input data are transformed several times and the different transformed data are applied as if they were independent inputs and are classified using stage neural networks. Finally, the outputs from the stage networks are then weighted and combined to make a decision. Experimental results based on remote sensing data and geographic data are given. The performance of the consensual neural network architecture is compared to that of a two-layer (one hidden layer) conjugate-gradient backpropagation neural network. The results with the proposed neural network architecture compare favorably in terms of classification accuracy to the backpropagation method.

Benediktsson, J. A.↗
DOE OSTI2023

Neural network denoising of HED x-ray images, with an introduction to neural networks [Slides]

We created and trained a new neural network denoiser model using estimates of noise in the data. We showed that our denoiser significantly reduces the combined blur and noise on the training and testing set. We demonstrated the efficacy of neural network denoisers for reducing noise on HED x-ray images. Changes to network architecture and improvements to the noise model in training could improve the model.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Neural Network Water Model Based on the MB-Pol Many-Body Potential

The MB-pol many-body potential accurately predicts many properties of water, including cluster, liquid phase, and vapor–liquid equilibrium properties, but its high computational cost can make applying it in large-scale simulations quite challenging. Here, in order to address this limitation, we developed a “deep potential” neural network (DPMD) model based on the MB-pol potential for water. We find that a DPMD model trained on mostly liquid configurations yields a good description of the bulk liquid phase but severely underpredicts vapor–liquid coexistence densities. By contrast, adding cluster configurations to the neural network training set leads to a good agreement for the vapor coexistence densities. Liquid phase densities under supercooled conditions are also represented well, even though they were not included in the training set. These results confirm that neural network models can combine accuracy and transferability if sufficient attention is given to the construction of a representative training set for the target system.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Stability Analysis of Substituted Cobaltocenium [Bis(cyclopentadienyl)cobalt(III)] Employing Chemistry-Informed Neural Networks

Cobaltocenium derivatives are promising components of the anion exchange membranes due to their excellent thermal and alkaline stability under the operating conditions of a fuel cell. Here we present an efficient modeling approach of assessing the chemical stability of substituted cobaltocenium CoCp 2 + based on the computed electronic structure enhanced by machine learning techniques. Within the aqueous environment, the positive charge of the metal cation is balanced by the hydroxide anion through formation of the CoCp 2 + OH¯ complexes, whose dissociation is studied within the implicit solvent employing density functional theory. The data set of about 118 species based on 42 substituent groups characterized by a range of electron- donating (ED) and electron-withdrawing (EW) properties is constructed and analyzed. Given 12 carefully chosen chemistry-informed descriptors of the complexes and relevant fragments, the stability of the complexes is found to strongly correlate with the energies of the highest occupied and lowest unoccupied molecular orbitals, modulated by a switching function of the Hirshfeld charge. The latter is used as a measure of the electron withdrawing-donating character of the substituents. Based on this observation from the conventional regression analysis, two fully connected, feed-forward neural network (FNN) models with different unit structures, called the chemistry-informed (CINN) and the quadratic (QNN) neural networks, are developed. Both models predict the bond dissociation energies of the cobaltocenium complexes with mean relative errors less than 5.40% and average absolute errors less than 0.94 kcal/mol. The results show the potential of QNN to efficiently capture more complex relationships. Here, the concept of incorporating the domain (chemical) knowledge/insight into the neural network structure paves the way to applications of machine learning techniques with small data sets, ultimately leading to better predictive models compared to the conventional regression analysis.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers

This paper presents a graph neural network (GNN) technique for low-level reconstruction of neutrino interactions in a Liquid Argon Time Projection Chamber (LArTPC). GNNs are still a relatively novel technique, and have shown great promise for similar reconstruction tasks in the LHC. In this paper, a multihead attention message passing network is used to classify the relationship between detector hits by labelling graph edges, determining whether hits were produced by the same underlying particle, and if so, the particle type. The trained model is 84% accurate overall, and performs best on the EM shower and muon track classes. The model’s strengths and weaknesses are discussed, and plans for developing this technique further are summarised.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Variational Monte Carlo Calculations of A ≤ 4 Nuclei with an Artificial Neural-Network Correlator Ansatz

Here, the complexity of many-body quantum wave functions is a central aspect of several fields of physics and chemistry where nonperturbative interactions are prominent. Artificial neural networks (ANNs) have proven to be a flexible tool to approximate quantum many-body states in condensed matter and chemistry problems. In this work we introduce a neural-network quantum state ansatz to model the ground-state wave function of light nuclei, and approximately solve the nuclear many-body Schrodinger equation. Using efficient stochastic sampling and optimization schemes, our approach extends pioneering applications of ANNs in the field, which present exponentially scaling algorithmic complexity. We compute the binding energies and point-nucleon densities of A ≤ 4 nuclei as emerging from a leading-order pionless effective field theory Hamiltonian. We successfully benchmark the ANN wave function against more conventional parametrizations based on two- and three-body Jastrow functions, and virtually exact Green's function Monte Carlo results.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

SyReNN: A tool for analyzing deep neural networks

Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety of important domains. Unfortunately, modern DNNs have been shown to be vulnerable to a variety of attacks and buggy behavior. This has motivated recent work in formally analyzing the properties of such DNNs. Furthermore, this paper introduces SyReNN, a tool for understanding and analyzing a DNN by computing its symbolic representation. The key insight is to decompose the DNN into linear functions. Our tool is designed for analyses using low-dimensional subsets of the input space, a unique design point in the space of DNN analysis tools. We describe the tool and the underlying theory, then evaluate its use and performance on three case studies: computing Integrated Gradients, visualizing a DNN’s decision boundaries, and repairing buggy DNNs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Jensen–Shannon divergence based novel loss functions for Bayesian neural networks

Bayesian neural networks (BNNs) are state-of-the-art machine learning methods that can naturally regularize and systematically quantify uncertainties using their stochastic parameters. Kullback–Leibler (KL) divergence-based variational inference used in BNNs suffer from unstable optimization and challenges in approximating light-tailed posteriors due to the unbounded nature of the KL divergence. To resolve these issues, we formulate a novel loss function for BNNs based on a new modification to the generalized Jensen–Shannon (JS) divergence, which is bounded. In addition, we propose a Geometric JS divergence-based loss, which is computationally efficient since it can be evaluated analytically. We found that the JS divergence-based variational inference is intractable, and hence employed a constrained optimization framework to formulate these losses. Our theoretical analysis and empirical experiments on multiple regression and classification data sets suggest that the proposed losses perform better than the KL divergence-based loss, especially when the data sets are noisy or biased. Specifically, there are approximately 5% and 8% improvements in accuracy for a noise-added CIFAR-10 dataset and a regression dataset, respectively. There is about 13% reduction in false negative predictions of a biased histopathology dataset. Additionally, we quantify and compare the uncertainty metrics for the regression and classification tasks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Self-regulating power management for a neural network system

A neural network runs a known input data set using an error free power setting and using an error prone power setting. The differences in the outputs of the neural network using the two different power settings determine a high level error rate associated with the output of the neural network using the error prone power setting. If the high level error rate is excessive, the error prone power setting is adjusted to reduce errors by changing voltage and/or clock frequency utilized by the neural network system. If the high level error rate is within bounds, the error prone power setting can remain allowing the neural network to operate with an acceptable error tolerance and improved efficiency. The error tolerance can be specified by the neural network application.

Kegel, Andrew G.↗
DOE OSTI2023

Self-regulating power management for a neural network system

A neural network runs a known input data set using an error free power setting and using an error prone power setting. The differences in the outputs of the neural network using the two different power settings determine a high level error rate associated with the output of the neural network using the error prone power setting. If the high level error rate is excessive, the error prone power setting is adjusted to reduce errors by changing voltage and/or clock frequency utilized by the neural network system. If the high level error rate is within bounds, the error prone power setting can remain allowing the neural network to operate with an acceptable error tolerance and improved efficiency. The error tolerance can be specified by the neural network application.

Kegel, Andrew G.↗
DOE OSTI2023

Neural network ensembles and uncertainty estimation for predictions of inelastic mechanical deformation using a finite element method-neural network approach

The finite element method (FEM) is widely used to simulate a variety of physics phenomena. Approaches that integrate FEM with neural networks (NNs) are typically leveraged as an alternative to conducting expensive FEM simulations in order to reduce the computational cost without significantly sacrificing accuracy. However, these methods can produce biased predictions that deviate from those obtained with FEM, since these hybrid FEM-NN approaches rely on approximations trained using physically relevant quantities. In this work, an uncertainty estimation framework is introduced that leverages ensembles of Bayesian neural networks to produce diverse sets of predictions using a hybrid FEM-NN approach that approximates internal forces on a deforming solid body. The uncertainty estimator developed herein reliably infers upper bounds of bias/variance in the predictions for a wide range of interpolation and extrapolation cases using a three-element FEM-NN model of a bar undergoing plastic deformation. This proposed framework offers a powerful tool for assessing the reliability of physics-based surrogate models by establishing uncertainty estimates for predictions spanning a wide range of possible load cases.

42 ENGINEERING↗
DOE OSTI2021

Energy-efficient Mott activation neuron for full-hardware implementation of neural networks

To circumvent the von Neumann bottleneck, substantial progress has been made towards in-memory computing with synaptic devices. However, compact nanodevices implementing non-linear activation functions are required for efficient full-hardware implementation of deep neural networks. Here, in this work, we present an energy-efficient and compact Mott activation neuron based on vanadium dioxide and its successful integration with a conductive bridge random access memory (CBRAM) crossbar array in hardware. The Mott activation neuron implements the rectified linear unit function in the analogue domain. The neuron devices consume substantially less energy and occupy two orders of magnitude smaller area than those of analogue complementary metal–oxide semiconductor implementations. The LeNet-5 network with Mott activation neurons achieves 98.38% accuracy on the MNIST dataset, close to the ideal software accuracy. We perform large-scale image edge detection using the Mott activation neurons integrated with a CBRAM crossbar array. Our findings provide a solution towards large-scale, highly parallel and energy-efficient in-memory computing systems for neural networks.

electrical and electronic engineering↗