Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Natural Language Processing”

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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Adapting In Situ Accelerators for Sparsity With Granular Matrix Reordering

Neural network (NN) inference is an essential part of modern systems and is found at the heart of numerous applications ranging from image recognition to natural language processing. In situ NN accelerators can efficiently perform NN inference using resistive crossbars, which makes them a promising solution to the data movement challenges faced by conventional architectures. Although such accelerators demonstrate significant potential for dense NNs, they often do not benefit from sparse NNs, which contain relatively few non-zero weights. Processing sparse NNs on in situ accelerators results in wasted energy to charge the entire crossbar where most elements are zeros. To address this limitation, this paper proposes Granular Matrix Reordering (GMR): a preprocessing technique that enables an energy-efficient computation of sparse NNs on in situ accelerators. GMR reorders the rows and columns of sparse weight matrices to maximize the crossbars' utilization and minimize the total number of crossbars needed to be charged. The reordering process does not rely on sparsity patterns and incurs no accuracy loss. Finally, GMR achieves an average of 28% and up to 34% reduction in energy consumption over seven pruned NNs across four different pruning methods and network architectures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Multimodal biological analysis using NLP and expression profile

The goal of this project is to gather biological data from different sources and use computational analysis to evaluate it together. Two data sources were used: microarray gene expression data for Arabidopsis thaliana, and gene co-occurrences in scientific literature extracted from bioRxiv using natural language processing (NLP). For analysis, the microarray data was normalized, its dimensionality was reduced using principal component analysis (PCA), and it was grouped into different numbers of clusters using K-means clusters. Then these expression clusters were compared to the co-occurrence pairs in the NLP data, to evaluate the quality of the NLP extractions. This evaluation was done using entropy analysis on the combined data, compared to the maximum entropy in the clustering alone. As a result, the evaluation of the NLP data shows that the results do correspond to the clusters from the microarray data, and may be used for further analysis.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Performance Analysis of Deep Learning Workloads on Leading-edge Systems

This work examines the performance of leading-edge systems designed for machine learning computing, including the NVIDIA DGX-2, Amazon Web Services (AWS) P3, IBM Power System Accelerated Compute Server AC922, and a consumer-grade Exxact TensorEX TS4 GPU server. Representative deep learning workloads from the fields of computer vision and natural language processing are the focus of the analysis. Performance analysis is performed along with a number of important dimensions. Performance of the communication interconnects and large and high-throughput deep learning models are considered. Different potential use models for the systems as standalone and in the cloud also are examined. The effect of various optimization of the deep learning models and system configurations is included in the analysis.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Exploring Capability of Multimodal Foundation Model for Image-based Fault Detection of Photovoltaic Modules

Multimodal Foundation Model (MFM), like ChatGPT and Gemini, have emerged as powerful tools for their exceptional natural language processing capabilities and their emerging potential in image analysis. This paper investigates the application of MFMs for photovoltaic (PV) fault detection through image analysis, focusing on ChatGPT 4.0 and Gemini 1.5 Pro. Three types of PV images and the corresponding common PV faults are detected: bird droppings using visible images, cell cracks via electroluminescence (EL) images, and hotspots using infrared (IR) images. Among the two models, Gemini 1.5 Pro demonstrated superior performance, achieving near-perfect results with an average F1 score of 0.97, consistently outperforming ChatGPT 4.0 in accuracy and reliability. Unlike traditional machine learning (ML) models, MFMs can operate in a zero shot manner that does not require additional training by the user, and the input images are not limited by size, angle, scope, or PV technology. The strong adaptability and user-friendliness make MFM a promising tool for analyzing PV images and advancing health monitoring for PV modules.

Li, Baojie↗
DOE OSTI2020

Scalable Knowledge Graph Analytics at 136 Petaflop/s

We are motivated by newly proposed methods for data mining large-scale corpora of scholarly publications, such as the full biomedical literature, which may consist of tens of millions of papers spanning decades of research. In this setting, analysts seek to discover how concepts relate to one another. They construct graph representations from annotated text databases and then formulate the relationship-mining problem as one of computing all-pairs shortest paths (APSP), which becomes a significant bottleneck. In this context, we present a new high-performance algorithm and implementation of the Floyd-Warshall algorithm for distributed-memory parallel computers accelerated by GPUs, which we call DSNAPSHOT (Distributed Accelerated Semiring All-Pairs Shortest Path). For our largest experiments, we ran DSNAPSHOT on a connected input graph with millions of vertices using 4, 096nodes (24,576GPUs) of the Oak Ridge National Laboratory's Summit supercomputer system. We find DSNAPSHOT achieves a sustained performance of 136×1015 floating-point operations per second (136petaflop/s) at a parallel efficiency of 90% under weak scaling and, in absolute speed, 70% of the best possible performance given our computation (in the single-precision tropical semiring or “min-plus” algebra). Looking forward, we believe this novel capability will enable the mining of scholarly knowledge corpora when embedded and integrated into artificial intelligence-driven natural language processing workflows at scale.

Kannan, Ramakrishnan {ramki}↗
DOE OSTI2019

Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids

The availability of fine grained time series data is a pre-requisite for research in smart-grids. While data for transmission systems is relatively easily obtainable, issues related to data collection, security and privacy hinder the widespread public availability/accessibility of such datasets at the distribution system level. This has prevented the larger research community from effectively applying sophisticated machine learning algorithms to significantly improve the distribution-level accuracy of predictions and increase the efficiency of grid operations. Synthetic dataset generation has proven to be a promising solution for addressing data availability issues in various domains such as computer vision, natural language processing and medicine. However, its exploration in the smart grid context remains unsatisfactory. Previous works have tried to generate synthetic datasets by modeling the underlying system dynamics: an approach which is difficult, time consuming, error prone and often times infeasible in many problems. In this work, we propose a novel data-driven approach to synthetic dataset generation by utilizing deep generative adversarial networks (GAN) to learn the conditional probability distribution of essential features in the real dataset and generate samples based on the learned distribution. To evaluate our synthetically generated dataset, we measure the maximum mean discrepancy (MMD) between real and synthetic datasets as probability distributions, and show that their sampling distance converges. To further validate our synthetic dataset, we perform common smart grid tasks such as k-means clustering and short-term prediction on both datasets. Experimental results show the efficacy of our synthetic dataset approach: the real and synthetic datasets are indistinguishable by solely examining the output of these tasks.

14 SOLAR ENERGY↗
DOE OSTI2022

Accelerating Hydraulic Fracture Imaging by Deep Transfer Learning

Deep transfer learning has a great success story in computer vision (CV), natural language processing, and many other fields. In this communication, we are going to push forward the deep transfer learning to the hydraulic fracture imaging problem by proposing a two-step approach: 1) train a convolutional neural network (CNN) to reconstruct target geometries by a relatively large amount of approximated field patterns generated from a simplified model and 2) fine-tune the top layers of transferred CNN by a small amount of true field patterns generated through a full model. The advantages include the rapid generation of large amount of data through the simplified model and the high reconstruction accuracy through a careful design of the deep transfer learning. Here, the CNN trained through the deep transfer learning can accurately reconstruct the lateral extent and direction of fractures with unseen conductivity and white Gaussian noise, showing a notable acceleration/accuracy enhancement over the previous CNN trained by mixing a small number of true data into the approximated data as data augmentation.

02 PETROLEUM↗
DOE OSTI2016

Cross-Domain Recognition by Identifying Joint Subspaces of Source Domain and Target Domain

This paper introduces here a new method to solve the cross-domain recognition problem. Different from the traditional domain adaption methods which rely on a global domain shift for all classes between the source and target domains, the proposed method is more flexible to capture individual class variations across domains. By adopting a natural and widely used assumption that the data samples from the same class should lay on an intrinsic low-dimensional subspace, even if they come from different domains, the proposed method circumvents the limitation of the global domain shift, and solves the cross-domain recognition by finding the joint subspaces of the source and target domains. Specifically, given labeled samples in the source domain, we construct a subspace for each of the classes. Then we construct subspaces in the target domain, called anchor subspaces, by collecting unlabeled samples that are close to each other and are highly likely to belong to the same class. The corresponding class label is then assigned by minimizing a cost function which reflects the overlap and topological structure consistency between subspaces across the source and target domains, and within the anchor subspaces, respectively. We further combine the anchor subspaces to the corresponding source subspaces to construct the joint subspaces. Subsequently, one-versus-rest support vector machine classifiers are trained using the data samples belonging to the same joint subspaces and applied to unlabeled data in the target domain. We evaluate the proposed method on two widely used datasets: 1) object recognition dataset for computer vision tasks and 2) sentiment classification dataset for natural language processing tasks. Comparison results demonstrate that the proposed method outperforms the comparison methods on both datasets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Visual Exploration of Semantic Relationships in Neural Word Embeddings

Constructing distributed representations for words through neural language models and using the resulting vector spaces for analysis has become a crucial component of natural language processing (NLP). But, despite their widespread application, little is known about the structure and properties of these spaces. To gain insights into the relationship between words, the NLP community has begun to adapt high-dimensional visualization techniques. Particularly, researchers commonly use t-distributed stochastic neighbor embeddings (t-SNE) and principal component analysis (PCA) to create two-dimensional embeddings for assessing the overall structure and exploring linear relationships (e.g., word analogies), respectively. Unfortunately, these techniques often produce mediocre or even misleading results and cannot address domain-specific visualization challenges that are crucial for understanding semantic relationships in word embeddings. We introduce new embedding techniques for visualizing semantic and syntactic analogies, and the corresponding tests to determine whether the resulting views capture salient structures. Additionally, we introduce two novel views for a comprehensive study of analogy relationships. Finally, we augment t-SNE embeddings to convey uncertainty information in order to allow a reliable interpretation. Combined, the different views address a number of domain-specific tasks difficult to solve with existing tools.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Bayesian, Multifidelity Operator Learning for Complex Engineering Systems–A Position Paper

Abstract Deep learning has significantly improved the state-of-the-art in computer vision and natural language processing, and holds great potential to design effective tools for predicting and simulating complex engineering systems. In particular, scientific machine learning seeks to apply the power of deep learning to scientific and engineering tasks, with operator learning (OL) emerging as a particularly effective tool. OL can approximate nonlinear operators arising in complex engineering systems, making it useful for simulating, designing, and controlling those systems. In this position paper, we provide a comprehensive overview of OL, including its potential applications to complex engineering domains. We cover three variations of OL approaches: deterministic OL for modeling nonautonomous systems, OL with uncertainty quantification (UQ) capabilities, and multifidelity OL. For each variation, we discuss drawbacks and potential applications to engineering, in addition to providing a detailed explanation. We also highlight how multifidelity OL approaches with UQ capabilities can be used to design, optimize, and control engineering systems. Finally, we outline some potential challenges for OL within the engineering domain.

Computer Science↗
DOE OSTI2023

Lorentz group equivariant autoencoders

Abstract There has been significant work recently in developing machine learning (ML) models in high energy physics (HEP) for tasks such as classification, simulation, and anomaly detection. Often these models are adapted from those designed for datasets in computer vision or natural language processing, which lack inductive biases suited to HEP data, such as equivariance to its inherent symmetries. Such biases have been shown to make models more performant and interpretable, and reduce the amount of training data needed. To that end, we develop the Lorentz group autoencoder (LGAE), an autoencoder model equivariant with respect to the proper, orthochronous Lorentz group $$\textrm{SO}^+(3,1)$$ SO + ( 3 , 1 ) , with a latent space living in the representations of the group. We present our architecture and several experimental results on jets at the LHC and find it outperforms graph and convolutional neural network baseline models on several compression, reconstruction, and anomaly detection metrics. We also demonstrate the advantage of such an equivariant model in analyzing the latent space of the autoencoder, which can improve the explainability of potential anomalies discovered by such ML models.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Provenance infrastructure for multimodal x-ray experiments and reproducible analysis

Exploring relationships between material structures and desired properties for material discovery and synthesis requires mining machine-readable databases and linking experimental data with sufficiently rich annotations. There are vast gaps both in these data sources and in the connections between them. We present a provenance-based data management and analysis framework that enables capturing, persisting, and reanalyzing experimental data from the BNL National Synchrotron Light Source II (NSLS-II). Our system leverages NSLS-II Bluesky for experimental data acquisition, captures analysis parameters, and enriches the search space with results from the scientific literature. We describe in detail the challenges and benefits of data-driven approaches when comparing computational and experimental data, such as the multiple possible scenarios of interest in often ill-posed inverse problems and missing data. Our infrastructure utilizes the NSLS-II event model and includes discovery mechanisms across multiple beamlines. A text and data mining module using natural language processing classification techniques extracts relevant information from the literature that is added to data sources. We describe a provenance acquisition and analysis rerun workflow based on a directed acyclic graph that keeps track of process and data provenance and allows to replay analysis.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

Facility Detection and Popularity Assessment from Text Classification of Social Media and Crowdsourced Data

Advances in technology have continually progressed our understanding of where people are, how they use the environment around them, and why they are at their current location. Having a better knowledge of when various locations become popular through space and time could have large impacts on research fields like urban dynamics and energy consumption. In this paper, we discuss the ability to identify and locate various facility types (e.g. restaurant, airport, stadiums) using social media, and assess methods in determining when these facilities become popular over time. We use natural language processing tools and machine learning classifiers to interpret geotagged Twitter text and determine if a user is seemingly at a location of interest when the tweet was sent. On average our classifiers are approximately 85% accurate varying across multiple facility types, with a peak precision of 98%. By using these methods to classify unstructured text, geotagged social media data can be an extremely useful tool to better understanding the composition of places and how and when people use them.

crowd-sourced data↗
DOE OSTI2018

Machine Learning to Improve Retrieval by Category in Big Volunteered Geodata

Nowadays, Volunteered Geographic Information (VGI) is commonly used in research and practical applications. However, the quality assurance of such a geographic data remains a problem. In this study we use machine learning and natural language processing to improve record retrieval by category (e.g. restaurant, museum, etc.) from Wikimapia Points of Interest data. We use textual information contained in VGI records to evaluate its ability to determine the category label. The performance of the trained classifier is evaluated on the complete dataset and then is compared with its performance on regional subsets. Preliminary analysis shows significant difference in the classifier performance across the regions. Such geographic differences will have a significant effect on data enrichment efforts such as labeling entities with missing categories.

Sorokine, Alexandre↗
DOE OSTI2024

A Compound Data Poisoning Technique with Significant Adversarial Effects on Transformer-based Sentiment Classification Tasks

Transformer-based models have demonstrated much success in various natural language processing tasks. However, they are often vulnerable to adversarial attacks, such as data poisoning, which can intentionally fool the model into generating incorrect results. In this article, we present a novel, compound variant of a data poisoning attack on a transformer-based model that maximizes the poisoning effect while minimizing the scope of poisoning. Here we do so by combining the established data poisoning technique (label flipping) with a novel adversarial artifact selection and insertion technique aimed at minimizing detectability and the scope of the poisoning footprint. We find that by using a combination of these two techniques, we achieve a state-of-the-art attack success rate of approximately 90% while poisoning only 0.5% of the original training set, thus minimizing the scope and detectability of the poisoning action. These findings have the potential to advance the development of better data poisoning detection methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training

Large Language Models (LLMs) have demonstrated remarkable performance in various natural language processing tasks. However, the training of these models is computationally intensive and susceptible to faults, particularly in the attention mechanism, which is a critical component of transformer-based LLMs. In this paper, we investigate the impact of faults on LLM training, focusing on INF, NaN, and near-INF values in the computation results with systematic fault injection experiments. We observe the propagation patterns of these errors, which can trigger non-trainable states in the model and disrupt training, forcing the procedure to load from checkpoints. To mitigate the impact of these faults, we propose ATTNChecker, the first Algorithm-Based Fault Tolerance (ABFT) technique tailored for the attention mechanism in LLMs. ATTNChecker is designed based on fault propagation patterns of LLM and incorporates performance optimization to adapt to both system reliability and model vulnerability while providing lightweight protection for fast LLM training. Evaluations on four LLMs show that ATTNChecker on average incurs on average 7% overhead on training while detecting and correcting all extreme errors. Compared with the state-of-the-art checkpoint/restore approach, ATTNChecker reduces recovery overhead by up to 49×.

Liang, Yuhang [University of Alabama - Birmingham]↗
DOE OSTI2019

Active Learning for NLP Systems

This software implements an active learning framework for Natural Language Processing (NLP) systems. It is intended to be applied on scenarios where limited amount of labeled data is available to train a machine learning-based NLP classification system, but a large set of unlabeled documents exist. This software will point, from the set of unlabeled documents, which ones we should label next so that the overall performance of the classifier is improved.

Goncalves, AndreR↗
DOE OSTI2021

Codon2Vec v1.0

Background: Codon2Vec is an embedding neural network that predicts 'high' or 'low' gene expression directly from the protein-coding sequences. Embedding neural networks are commonly used for natural language processing (NLP) applications. Analogous to how an English sentence is a string of words, a gene can be thought of as a string of codons. Similar to how NLP neural networks model English sentences as a non-random sequence of words, we considered a coding sequence as a non-random non-overlapping array of codons (k-mers of length = 3). Value Proposition: - Codon2Vec achieved a high median AUC-ROC score of 83.8% when trained and applied to transcriptomic data from 300 fungal species - Unlike Codo2Vec, conventional methods predicting for expression based on codon usage rely on a priori knowledge of optimal codons or a set of reference genes. - Unlike Codon2vec, these methods do not account for the effect of codon order on gene expression. - Codon2Vec neural network bypasses the need for artisanal feature selection step that is necessary for traditional machine learning models.

Wint, Rhondene↗