Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “pruning”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Particle Track Classification Using Quantum Associative Memory (Final Technical Report)

This project explored the use of quantum-assisted algorithms for pattern matching in sub-atomic physics experiments. Pattern matching algorithms are commonly employed to prune data of random noise and to help discriminate between signals generated by particle tracks of interest and signals generated by background events. The quantum-assisted algorithms explored in this project were based on an Ising formulation of quantum associative model (QAMM) recall and quantum content-addressable memory (QCAM) recall. The recall is performed by comparing a probe pattern with those stored in a library of patterns encoded in the QAMM/QCAM model. The classification accuracy of QAMM and QCAM recall was determined as a function of detector resolution, noise, and efficiency and pattern density, where pattern density is defined as the ratio of the number of reference signal patterns encoded in the library to each pattern’s length. We found that QAMM achieved high classification accuracy when applied to datasets with low pattern density. QCAM achieved high classification accuracy for datasets with high pattern density and was found to be more robust to detector noise. The project methodology and results are described in detail in our arXiv preprint (arXiv:2011.11848) . This project was conducted by scientists at the Johns Hopkins University Applied Physics Laboratory and Oak Ridge National Laboratory from August 2018 to August 2020 and was supported by DOE grant DE-SC0019497.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

SMALE: Enhancing Scalability of Machine Learning Algorithms on Extreme-Scale Computing Platforms

Deployment and execution of machine learning tasks on extreme-scale computing platforms face several significant technical challenges: 1) High computing cost incurred by dense networks – The computing workload of deep networks with densely-connected topology increases rapidly with the network size, imposing a non-scalable computing model of extreme-scale computing platforms; 2) Non-optimized workload distribution – Many advanced deep learning algorithms, e.g., sparsification and irregular net-work topology, produce very unbalanced workload distribution on extreme-scale computing platforms. The computation efficiency is greatly hindered by the incurred data and computation redundancies as well as long tails of the node with extensive workload; 3) Constraints in data movement and I/O bottle-neck – Inter-node data movement in extreme-scale computing platforms are associated with high energy and latency costs, and subject to the constraints of I/O bandwidth; and 4) Generalization of algorithm realization and acceleration on computing platforms – The large varieties of machine learning algorithms and structures of extreme-scale computing platforms make the derivation of a generalized algorithm realization and acceleration method very challenging, which, however, is the requirement by domain scientists and interested users. We call the above challenges Smale’s Problems in Machine Learning and Understanding for High-Performance Computing Scientific Discovery. The objective of our three-year research project is to develop a holistic innovation set at structure, assembly, and acceleration layers of machine learning algorithms to address the above challenges in algorithm deployment and execution. Three tasks are particularly performed, including: At the algorithm structure level, we investigate the techniques that can structurally sparsify on the topology of deep networks for computing workload reduction. We also study clustering and pruning techniques that can optimize the workload distributions over the extreme-scale computing platforms; At the algorithm assembly level, we derive a unified learning framework for unsupervised transfer learning and dynamic growing capabilities. Novel training methods are also exploited to enhance the training efficiency of the proposed framework; At the algorithm acceleration level, we will develop a series of techniques that can accelerate the computation of sparse matrix operations, which are one of the core executions in deep learning and optimize memory access of the concerned platforms. Our proposed techniques attack the fundamental problems in machine learning algorithms running on extreme-scale computing platforms by vertically integrating the solutions at three closely entangled layers, paving the long-term scaling path of machine learning applications under DOE context. Three tasks corresponding to the above respective research orientations are performed during the three-year project period with our collaborators at ORNL. The outcome of the proposed project is anticipated to form a holistic solution set of novel algorithms and network topologies, efficient training techniques, and fast acceleration methods to promote the computing scalability of the machine learning applications of particular interest to DOE.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Extending Parsimonious Bayesian Inference

Parsimonious Bayesian inference is a theoretical framework for efficient data assimilation that seeks to balance increased consistency between predictions and training data against corresponding increases in model complexity. Within this framework, over-training is understood as optimization that encodes excessive information within model parameters while only achieving small improvements between predictions and training data. This project aims to develop practical methods of limiting excess model information during optimization. One key observation is that practical heuristics for parsimonious learning in high-dimensions must balance expressivity, i.e. the ability of the model to capture diverse predictions with only a few non-zero parameters, against discoverability, i.e. the ability to train the model with gradient-based optimization and drive parameters to low information states. As such, we developed logical activation functions that are able to adaptively approximate arbitrary truth tables that define Boolean logic operations within a probabilistic framework. These functions have demonstrated the ability to learn exclusive disjunction (XOR) and conditioned disjunction (if [condition] then [result_if_true] else [result_if_false]) within a single layer of a neural network. To efficiently exploit these activation functions to drive parsimonious learning required several other advances within the domain of variational inference. The most efficient form of complexity suppression is structured sparsification, driving most model parameters to zero while achieving the structural coherence among nonzeros needed for bandwidth reduction. Such models are not only far more efficient at suppressing information-theoretic complexity, they also reduce the other forms of complexity (computations, communication, storage, and the number of dependencies needed to evaluate predictions). Aiming to support enhanced sparsification, this project examined new approaches to high-dimensional variational inference that allow us to calibrate and control parameter uncertainty during optimization. By identifying which parameters can sustain sparsifying perturbations with little impact on prediction quality, we can develop better pruning strategies by framing them as approximate Bayesian inference. These advances also open paths to mitigate concerns with deploying advanced learning methods in resource-constrained environments, such as running models on power-limited or communication-limited devices.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Using AMReX's Embedded Boundaries to Support MFIX-Exa’s Geometry Capabilities

MFIX-Exa is an AMReX-based application used for the simulation of chemically reacting multiphase flows inside reactors. The reactor geometry is mostly a combination of primitive shapes such as cylinders, cubes and spheres of varying dimensions connected together with potentially a lot of dead space between them. Additionally, the reactors may have particle-laden jets introduced at different parts of their geometry to enhance reactant mixing. This talk presents how MFIX-Exa uses OpenSCAD’s csg format to allow users to define the embedded boundary (EB) geometry and how it supports specifying inflow through certain sections of the EB. The talk will describe how MFIX-Exa leverages the EB features of grid-pruning, restart files and redistribution. Finally, the talk goes over some capabilities which are currently not available in MFIX-Exa but planned for the future, such as moving parts of the reactor geometry.

embedded boundaries↗
DOE OSTI2025

Scalable workflow for evaluating and optimizing large language models

This work describes the improved workflow for evaluating open-source large language models (LLMs) for trustworthiness. The workflow facilitates the acquisition of LLMs, the generation of LLM responses, and the evaluation of the responses for their trustworthiness. As a use case, the workflow is employed to evaluate dense, quantized, and pruned Meta Llama3.1 LLMs for their truthfulness. The outcome of the project could set the stage for understanding and developing trustworthy models in the future projects.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Low-latency Jet Tagging for HL-LHC Using Transformer Architectures

Transformers are the state-of-the-art model architectures and widely used in application areas of machine learning. However the performance of such architectures is less well explored in the ultra-low latency domains where deployment on FPGAs or ASICs is required. Such domains include the trigger and data acquisition systems of the LHC experiments. We present a transformer-based algorithm for jet tagging built with the HGQ2 framework, which is able to produce a model with heterogeneous bitwidths for fast inference on FPGAs, as required in the trigger systems at the LHC experiments. The bitwidths are acquired during training by minimizing the total bit operations as an additional parameter. By allowing a bitwidth of zero, the model is pruned in-situ during training. Using this quantization-aware approach, our algorithm achieves state-of-the-art performance while also retaining permutation invariance which is a key property for particle physics applications. Due to the strength of transformers in representation learning, our work also serves as a stepping stone for the development of a larger foundation model for trigger applications.

Laatu, Lauri [Imperial Coll., London]↗
DOE OSTI2023

Robust Resilient Signal Reconstruction under Adversarial Attacks

We consider the problem of signal reconstruction for a system under sparse signal corruption by a malicious agent. The reconstruction problem follows the standard error coding problem that has been studied extensively in the literature. We include a new challenge of robust estimation of the attack support. The problem is then cast as a constrained optimization problem merging promising techniques in the area of deep learning and estimation theory. A pruning algorithm is developed to reduce the "false positive" uncertainty of data-driven attack localization results, thereby improving the probability of correct signal reconstruction. Sufficient conditions for the correct reconstruction and the associated reconstruction error bounds are obtained for both exact and inexact attack support estimation. Moreover, a simulation of a water distribution system is presented to validate the proposed techniques.

Robust, Signal reconstruction, Resilient estimator↗
DOE OSTI2023

Selecting Minimal Motion Primitive Libraries with Genetic Algorithms

Motion primitives allow for application of discrete search algorithms to rapidly produce trajectories in complex continuous space. The maneuver automaton (MA) provides an elegant formulation for creating a primitive library based on trims and maneuvers. However, performance is fundamentally limited by the contents of the primitive library. If the library is too sparse, performance can be poor in terms of path cost, whereas a library that is too large can increase run time. This work outlines new methods for using genetic algorithms to prune a primitive library. The proposed methods balance the path cost and planning time while maintaining the reachability of the MA. The genetic algorithm in this paper evaluates and mutates populations of motion primitive libraries to optimize both objectives. Here, we illustrate the performance of these methods with a simulated study using a nonlinear medium-fidelity F-16 model. We optimize a library with the presented algorithm for obstacle-free navigation and a nap-of-the-Earth navigation task. In the obstacle-free navigation task, we show a tradeoff of a 10.16% higher planning cost for a 96.63% improvement in run time. In the nap-of-the-Earth task, we show a tradeoff of a 9.712% higher planning cost for a 92.06% improvement in run time.

42 ENGINEERING↗
DOE OSTI2024

Autonomous Emergency Landing for Fixed-Wing Aircraft with Energy-Constrained Closed-Loop Prediction

Here this paper presents a new approach for autonomous motion planning for aircraft suffering from a loss-of-thrust emergency. Specifically, we show how modifications to the Closed-Loop Rapidly exploring Random Trees (CL-RRT) framework combined with controlled energy dissipation can enable rapid and effective kinodynamic motion planning. This CL-RRT Glide algorithm uses closed-loop prediction not only for node connections but also to estimate the remaining energy and prune infeasible paths. This greatly speeds up the search process, which is essential for emergency situations. In addition, we improve the ability of the gliding aircraft to reach a goal position and energy state. We do so by creating a Dissipative Total Energy Control Scheme (TECS). Dissipative TECS enables the glider to lose excess altitude in order to reach a desired energy level. Simulation results illustrate how the proposed methods enable faster motion planning. We also integrate the system into a small unmanned aerial vehicle system and experimentally demonstrate autonomous glide planning and execution during a motor-failure event. This type of algorithm can primarily benefit unmanned aircraft but can also serve to assist pilots in stressful emergency situations.

42 ENGINEERING↗
DOE OSTI2026

Geographic_Distribution_of_Populus_trichocarpa_Genotypes_by_DBSCAN_Cluster

Aninteractive mapshowingPopulus trichocarpaGWAS sub-population structure identified by DBSCAN clustering, which were derived from a UMAP projection of the top 8 PCs of LD-pruned pangenome SNP data. Geographic origins are searchable by genotype or river system using the search bar.

09 BIOMASS FUELS↗
DOE OSTI2024

Cross-Feature Transfer Learning for Efficient Tensor Program Generation

Tuning tensor program generation involves navigating a vast search space to find optimal program transformations and measurements for a program on the target hardware. The complexity of this process is further amplified by the exponential combinations of transformations, especially in heterogeneous environments. This research addresses these challenges by introducing a novel approach that learns the joint neural network and hardware features space, facilitating knowledge transfer to new, unseen target hardware. A comprehensive analysis is conducted on the existing state-of-the-art dataset, TenSet, including a thorough examination of test split strategies and the proposal of methodologies for dataset pruning. Leveraging an attention-inspired technique, we tailor the tuning of tensor programs to embed both neural network and hardware-specific features. Notably, our approach substantially reduces the dataset size by up to 53% compared to the baseline without compromising Pairwise Comparison Accuracy (PCA). Furthermore, our proposed methodology demonstrates competitive or improved mean inference times with only 25–40% of the baseline tuning time across various networks and target hardware. The attention-based tuner can effectively utilize schedules learned from previous hardware program measurements to optimize tensor program tuning on previously unseen hardware, achieving a top-5 accuracy exceeding 90%. This research introduces a significant advancement in autotuning tensor program generation, addressing the complexities associated with heterogeneous environments and showcasing promising results regarding efficiency and accuracy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Entropy-Assisted Quality Pattern Identification in Finance

Short-term patterns in financial time series form the cornerstone of many algorithmic trading strategies, yet extracting these patterns reliably from noisy market data remains a formidable challenge. In this paper, we propose an entropy-assisted framework for identifying high-quality, non-overlapping patterns that exhibit consistent behavior over time. We ground our approach in the premise that historical patterns, when accurately clustered and pruned, can yield substantial predictive power for short-term price movements. To achieve this, we incorporate an entropy-based measure as a proxy for information gain: patterns that lead to high one-sided movements in historical data yet retain low local entropy are more “informative” in signaling future market direction. Compared to conventional clustering techniques such as K-means and Gaussian Mixture Models (GMMs), which often yield biased or unbalanced groupings, our approach emphasizes balance over a forced visual boundary, ensuring that quality patterns are not lost due to over-segmentation. By emphasizing both predictive purity (low local entropy) and historical profitability, our method achieves a balanced representation of Buy and Sell patterns, making it better suited for short-term algorithmic trading strategies. This paper offers an in-depth illustration of our entropy-assisted framework through two case studies on Gold vs. USD and GBPUSD. While these examples demonstrate the method’s potential for extracting high-quality patterns, they do not constitute an exhaustive survey of all possible asset classes.

Physics↗
DOE OSTI2021

Multi-Area Distribution System State Estimation Using Decentralized Physics-Aware Neural Networks

The development of active distribution grids requires more accurate and lower computational cost state estimation. In this paper, the authors investigate a decentralized learning-based distribution system state estimation (DSSE) approach for large distribution grids. The proposed approach decomposes the feeder-level DSSE into subarea-level estimation problems that can be solved independently. The proposed method is decentralized pruned physics-aware neural network (D-P2N2). The physical grid topology is used to parsimoniously design the connections between different hidden layers of the D-P2N2. Monte Carlo simulations based on one-year of load consumption data collected from smart meters for a three-phase distribution system power flow are developed to generate the measurement and voltage state data. The IEEE 123-node system is selected as the test network to benchmark the proposed algorithm against the classic weighted least squares and state-of-the-art learning-based DSSE approaches. Numerical results show that the D-P2N2 outperforms the state-of-the-art methods in terms of estimation accuracy and computational efficiency.

24 POWER TRANSMISSION AND DISTRIBUTION↗
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↗
DOE OSTI2021

Grand unified file indexing

Systems and methods are disclosed for a unified file index for a file system. In one example, a Grand Unified File Index (GUFI) includes a tree replicating the directory hierarchy of one or more primary filesystems, and individual metadata stores for each directory. The GUFI tree permits fast traversal, efficient user space access controls, and simple tree directed operations such as renames, moves, or permission changes. In some examples, the individual metadata stores can be implemented as embedded databases on flash storage for speed. In some examples, use of summary tables at the directory or subtree level can eliminate wasteful executions, prune tree traversal, and further improve performance. In various examples, efficient operation can be achieved from laptop to supercomputer scale, across a wide mix of file distributions and filesystems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices

Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can drastically improve experimental design and accelerate scientific discoveries. To support domain scientists, we have developed hls4ml, an open-source software-hardware codesign workflow to interpret and translate machine learning algorithms for implementation with both FPGA and ASIC technologies. We expand on previous hls4ml work by extending capabilities and techniques towards low-power implementations and increased usability: new Python APIs, quantization-aware pruning, end-to-end FPGA workflows, long pipeline kernels for low power, and new device backends include an ASIC workflow. Taken together, these and continued efforts in hls4ml will arm a new generation of domain scientists with accessible, efficient, and powerful tools for machine-learning-accelerated discovery.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Automated Shift Detection in Sensor-Based PV Power and Irradiance Time Series

PV power and irradiance sensor-based measurements are prone to error, resulting in issues such as abrupt time series data shifts. These shifts, which are usually unintentional, may be caused by software or hardware configuration changes on a PV system, and do not reflect an actual change in overall system performance. Locating these shifts and segmenting the associated time series aids in more accurate future PV analysis. In this research, an offline changepoint detection (CPD) algorithm that automatically detects these abrupt data shifts in sensor-based time series is introduced. Data shift periods in 101 daily PV power and irradiance time series were labeled manually by two solar experts. These data streams represent sensor-based measurements, and display a variety of data shift behaviors. A changepoint detection algorithm was tuned using the 101 labeled data streams, with each model configuration's ability to detect labeled changepoints benchmarked using metrics such as F1-score, recall, and Rand Index. Best performing models on seasonality-corrected data streams include the Pruned Exact Linear (PELT) method, the Binary Segmentation method, and the Bottom-Up method, all scoring an average F1-score of 0.76 or greater at detecting labeled changepoints within a 30-day window for the labeled data sets. To promote further research in this space, we are releasing the labeled data shift sets on U.S. Department of Energy's (DOE) DuraMAT Data Hub, and the associated algorithm in the Python PVAnalytics package.

changepoint detection↗
DOE OSTI2022

Automated Shift Detection in Sensor-Based PV Power and Irradiance Time Series

PV power and irradiance sensor-based measurements are prone to error, resulting in issues such as time series data shifts. In this research, a changepoint detection (CPD) algorithm that automatically detects data shifts in sensor-based time series is introduced. Data shift periods in 101 daily PV power and irradiance time series were labeled manually by two solar experts. These data streams represent sensor-based measurements, and display a variety of data shift behaviors. A changepoint detection algorithm was tuned using the 101 labeled data streams, with each model configuration's ability to detect labeled changepoints benchmarked using metrics such as F1-score, recall, and Rand Index. Best performing models on seasonality-corrected data streams include the Pruned Exact Linear (PELT) method, the Binary Segmentation method, and the Bottom-Up method, all scoring an average F1-score of 0.76 or greater at detecting labeled changepoints within a 30-day window across the labeled data sets. Pending approval, we plan to release the labeled data sets for this research on NREL's DuraMAT Data Hub, and the associated algorithm in the Python PVAnalytics package. By supplying the training sets and algorithm, we hope to encourage further development in this research space.

data shift↗