Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “train”

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 433 records · Page 24
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Machine Learning Potentials with the Iterative Boltzmann Inversion: Training to Experiment

Methodologies for training machine learning potentials (MLPs) with quantum-mechanical simulation data have recently seen tremendous progress. Experimental data have a very different character than simulated data, and most MLP training procedures cannot be easily adapted to incorporate both types of data into the training process. Here, we investigate a training procedure based on iterative Boltzmann inversion that produces a pair potential correction to an existing MLP using equilibrium radial distribution function data. By applying these corrections to an MLP for pure aluminum based on density functional theory, we observe that the resulting model largely addresses previous overstructuring in the melt phase. Interestingly, the corrected MLP also exhibits improved performance in predicting experimental diffusion constants, which are not included in the training procedure. The presented method does not require autodifferentiating through a molecular dynamics solver and does not make assumptions about the MLP architecture. Our results suggest a practical framework for incorporating experimental data into machine learning models to improve the accuracy of molecular dynamics simulations.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Deep material network via a quilting strategy: visualization for explainability and recursive training for improved accuracy

Recent developments integrating micromechanics and neural networks offer promising paths for rapid predictions of the response of heterogeneous materials with similar accuracy as direct numerical simulations. The deep material network is one such approaches, featuring a multi-layer network and micromechanics building blocks trained on anisotropic linear elastic properties. Once trained, the network acts as a reduced-order model, which can extrapolate the material’s behavior to more general constitutive laws, including nonlinear behaviors, without the need to be retrained. However, current training methods initialize network parameters randomly, incurring inevitable training and calibration errors. Here, we introduce a way to visualize the network parameters as an analogous unit cell and use this visualization to “quilt” patches of shallower networks to initialize deeper networks for a recursive training strategy. The result is an improvement in the accuracy and calibration performance of the network and an intuitive visual representation of the network for better explainability.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

QUBO formulations for training machine learning models

Abstract Training machine learning models on classical computers is usually a time and compute intensive process. With Moore’s law nearing its inevitable end and an ever-increasing demand for large-scale data analysis using machine learning, we must leverage non-conventional computing paradigms like quantum computing to train machine learning models efficiently. Adiabatic quantum computers can approximately solve NP-hard problems, such as the quadratic unconstrained binary optimization (QUBO), faster than classical computers. Since many machine learning problems are also NP-hard, we believe adiabatic quantum computers might be instrumental in training machine learning models efficiently in the post Moore’s law era. In order to solve problems on adiabatic quantum computers, they must be formulated as QUBO problems, which is very challenging. In this paper, we formulate the training problems of three machine learning models—linear regression, support vector machine (SVM) and balanced k-means clustering—as QUBO problems, making them conducive to be trained on adiabatic quantum computers. We also analyze the computational complexities of our formulations and compare them to corresponding state-of-the-art classical approaches. We show that the time and space complexities of our formulations are better (in case of SVM and balanced k-means clustering) or equivalent (in case of linear regression) to their classical counterparts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Biologically-informed excitatory and inhibitory ratio for robust spiking neural network training

Spiking neural networks drawing inspiration from biological constraints of the brain promise an energy-efficient paradigm for artificial intelligence. However, challenges exist in identifying guiding principles to train these networks in a robust fashion. In addition, training becomes an even more difficult problem when incorporating biological constraints of excitatory and inhibitory connections. In this work, we identify several key factors, such as low initial firing rates and diverse inhibitory spiking patterns, that determine the overall ability to train in the context of spiking networks with various ratios of excitatory to inhibitory neurons. The results indicate networks with biologically-realistic excitatory:inhibitory ratios can reliably train at low activity levels and in noisy environments. Additionally, the Van Rossum distance, a measure of spike train synchrony, provides insight into the importance of inhibitory neurons to increase network robustness to noise. This work supports further biologically-informed large-scale networks and energy efficient hardware implementations.

bio-inspired computing↗
DOE OSTI2022

Training neural networks using Metropolis Monte Carlo and an adaptive variant

Abstract We examine the zero-temperature Metropolis Monte Carlo (MC) algorithm as a tool for training a neural network by minimizing a loss function. We find that, as expected on theoretical grounds and shown empirically by other authors, Metropolis MC can train a neural net with an accuracy comparable to that of gradient descent (GD), if not necessarily as quickly. The Metropolis algorithm does not fail automatically when the number of parameters of a neural network is large. It can fail when a neural network’s structure or neuron activations are strongly heterogenous, and we introduce an adaptive Monte Carlo algorithm (aMC) to overcome these limitations. The intrinsic stochasticity and numerical stability of the MC method allow aMC to train deep neural networks and recurrent neural networks in which the gradient is too small or too large to allow training by GD. MC methods offer a complement to gradient-based methods for training neural networks, allowing access to a distinct set of network architectures and principles.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Coarse-to-Fine Multi-Task Training of Convolutional Neural Networks for Automated Information Extraction from Cancer Pathology Reports

Information extraction and coding of free-text pathology reports is an important activity for cancer registries to support national cancer surveillance. Cancer registrars must process high volumes of pathology reports on an annual basis. In this study, we investigated an automated approach using a coarse-to-fine training of convolutional neural networks (CNNs) for extracting the primary site, histological grade and laterality from unstructured cancer pathology text reports. Our proposed training scheme consists of two stages. In the first stage, the multi-task learning (MTL) with hard parameter sharing approach is used to train a multi-task MT-CNN model for all the tasks. Then, the TM-CNN parameters are used to initialize a CNN model for each task to be fine trained individually using its corresponding dataset. The performance of our proposed model was compared against a state-of-the-art CNN and the commonly used SVM classifier. We observed that the proposed model consistently outperformed the base line models, especially for the less prevalent classes. Specifically, the proposed training approach achieved a micro-F score of 0.7749 over 12 ICD- O-3 topography codes which is a significant improvement as compared with state-of-the-art CNN (0.7101) and the SVM (0.6019) classifiers. Also, the results demonstrate the potential of the proposed method for handling class imbalance within each task. It significantly improves macro-F score by 24% and 12% of the primary site and histology grade tasks, respectively.

Alawad, Mohammed↗
DOE OSTI2020

Training Spiking Neural Networks Using Combined Learning Approaches

Spiking neural networks (SNNs), the class of neural networks used in neuromorphic computing, are difficult to train using traditional back-propagation techniques. Spike timingdependent plasticity (STDP) is a biologically inspired learning mechanism that can be used to train SNNs. Evolutionary algorithms have also been demonstrated as a method for training SNNs. In this work, we explore the relationship between these two training methodologies. We evaluate STDP and evolutionary optimization as standalone methods for training networks, and also evaluate a combined approach where STDP weight updates are applied within an evolutionary algorithm. We also apply Bayesian hyperparameter optimization as a meta learner for each of the algorithms. We find that STDP by itself is not an ideal learning rule for randomly connected networks, while the inclusion of STDP within an evolutionary algorithm leads to similar performance, with a few interesting differences. This study suggests future work in understanding the relationship between network topology and learning rules.

Elbrecht, Daniel↗
DOE OSTI2020

Layer-Parallel Training of Deep Residual Neural Networks

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, parallel-in-time methods have shown notable improvements in scalability. This paper demonstrates the use of those techniques for efficient and effective training of ResNets. The proposed algorithms replace the classical (sequential) forward and backward propagation through the network layers with a parallel nonlinear multigrid iteration applied to the layer domain. This adds a new dimension of parallelism across layers that is attractive when training very deep networks. From this basic idea, we derive multiple layer-parallel methods. The most efficient version employs a simultaneous optimization approach where updates to the network parameters are based on inexact gradient information in order to speed up the training process. Finally, using numerical examples from supervised classification, we demonstrate that the new approach achieves a training performance similar to that of traditional methods, but enables layer-parallelism and thus provides speedup over layer-serial methods through greater concurrency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

3D-ReG: A 3D ReRAM-based Heterogeneous Architecture for Training Deep Neural Networks

Deep neural network (DNN) models are being expanded to a broader range of applications. The computational capability of traditional hardware platforms cannot accommodate the growth of model complexity. Among recent technologies to accelerate DNN, resistive memory (ReRAM)-based processing-in-memory (PIM) emerged as a promising solution for DNN inference due to its high efficiency for matrix-based computation. We face two major technical challenges in extending the use of ReRAM-based accelerators for training: (1) full-precision data is essential in back-propagation; (2) the need to support both feed-forward and back-propagation aggravates the data-movement burden. We propose a heterogeneous architecture named as 3D-ReG, which leverages full-precision GPU to ensure training accuracy and low-overhead 3D integration to provide low-cost data movements. Moreover, we introduce conservative and aggressive task-mapping schemes, which partition the computation phases in different ways to balance execution efficiency and training accuracy. We evaluate 3D-ReG implemented with two 3D integration technologies, through-silicon vias (TSVs) and monolithic inter-tier vias (MIVs), and compare them with GPU-only and PIM-only counterparts. Various GPU-only platforms using two main-memory technologies (DRAM, ReRAM) and three interconnect technologies (2D, TSV, MIV) are evaluated as well. Experimental results show that 3D-ReG can achieve on average 5.64× training speedup and 3.56× higher energy efficiency compared with the GPU with DRAM as main memory, at the cost of 0.05%–3.39% accuracy drop. We define a new metric, gain-loss ratio (GLR), which quantitatively evaluates the capability of a DNN training hardware in terms of the model accuracy and hardware efficiency. The results of our comparison show that the aggressive task-mapping scheme on MIV-based 3D-ReG outperforms the other methods.

Computer Science↗
DOE OSTI2021

D2U: Data Driven User Emulation for the Enhancement of Cyber Testing, Training, and Data Set Generation

Whether testing intrusion detection systems, conducting training exercises, or creating data sets to be used by the broader cybersecurity community, realistic user behavior is a critical component of a cyber range. Existing methods either rely on network level data or replay recorded user actions to approximate real users in a network. Our work is the first to produce generative models trained on actual user data (sequences of application usage) collected on endpoints. Once trained to the user's behavioral data, these models can generate novel sequences of actions %that appear to come from the same distribution as the training data. These sequences of actions are then fed to our custom software via configuration files, which replicate those behaviors on end devices. Notably, our models are platform agnostic and could generate behavior data for any emulation software package. In this paper we present our model generation process, software architecture, and an initial evaluation of the fidelity of our models. Our software is currently deployed in a cyber range to help evaluate the efficacy of defensive cyber technologies. We suggest additional ways that the cyber community as a whole can benefit from more realistic user behavior emulation. The data used to train our model, as well as sample configuration files produced by the model, are available at [redacted].

Oesch, T↗
DOE OSTI2023

DDStore: Distributed Data Store for Scalable Training of Graph Neural Networks on Large Atomistic Modeling Datasets

Graph neural networks (GNNs) are a class of Deep Learning models used in designing atomistic materials for effective screening of large chemical spaces. To ensure robust prediction, GNN models must be trained on large volumes of atomistic data on leadership class supercomputers. Even with the advent of modern architectures that consist of multiple storage layers that include node-local NVMe devices in addition to device memory for caching large datasets, extreme-scale model training faces I/O challenges at scale.We present DDStore, an in-memory distributed data store designed for GNN training on large-scale graph data. DDStore provides a hierarchical, distributed, data caching technique that combines data chunking, replication, low-latency random access, and high throughput communication. DDStore achieves near-linear scaling for training a GNN model using up to 1000 GPUs on the Summit and Perlmutter supercomputers, and reaches up to a 6.15x reduction in GNN training time compared to state-of-the-art methodologies.

Choi, Jong Youl↗
DOE OSTI2024

Towards a High Fidelity Training Environment for Autonomous Cyber Defense Agents

Cyber defenders are overwhelmed by the frequency and scale of attacks against their networks. This problem will only be exacerbated as attackers leverage AI to automate their workflows. Autonomous cyber defense capabilities could aid defenders by automating operations and adapting dynamically to novel threats. However, existing training environments fall short in areas such as generalization, explainability, scalability, and transferability, making it intractable to train agents that will be effective in real networks. In this paper we take an important step towards creating autonomous cyber defense agents — we present a high fidelity training environment called Cyberwheel that includes both simulation and emulation capabilities. Cyberwheel simplifies customization of the training network and easily allows redefining the agent’s reward function, observation space, and action space to support rapid experimentation of novel approaches to agent design. It also provides visibility into agent behaviors necessary for agent evaluation and sufficient documentation / examples to lower the barrier to entry. As an example use case of Cyberwheel, we present initial results training an autonomous agent to deploy cyber deception strategies in simulation.

Oesch, T↗
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 OSTI2025

CAFE AU LAIT: Compute-Aware Federated Augmented Low-Rank AI Training

Federated finetuning is crucial for unlocking the knowledge embedded in pretrained Large Language Models (LLMs) when data are geographically distributed across clients. Unlike finetuning with data from a single institution, federated finetuning allows collaboration across multiple institutions, enabling the utilization of diverse and decentralized datasets while preserving data privacy. Given the high computing costs of LLM training and the emphasis on energy efficiency in Federated Learning (FL), Low-Rank Adaptation (LoRA) has emerged as a widely adopted algorithm due to its significantly reduced number of trainable parameters. However, this assumes that all data silos have the necessary computing resources to compute local updates of LLMs. Nevertheless, in practice, the computing resources across clients are highly heterogeneous: while some may have access to hundreds of GPUs, others might have limited or no GPU access. Recently, federated finetuning using synthetic data has been proposed, allowing clients to participate in a collaborative training run without training LLMs locally. However, our experimental results reveal a performance gap between models trained using synthetic data and those trained using local updates. Motivated by the observed heterogeneity in computing resources and the performance gap, we propose a novel two-stage algorithm that leverages the storage and computing capabilities of a strong server. In the first stage, under the coordination of the strong server, clients with limited computing resources collaborate to generate synthetic data, which is transferred to and stored on the strong server. In the second stage, the strong server uses this synthetic data on behalf of the resource-constrained clients to perform federated LoRA finetuning alongside clients with sufficient computing resources. This approach ensures that all clients can participate in the finetuning process. Experimental results demonstrate that incorporating local updates from even a small fraction of clients improves performance compared to using synthetic data for all clients. Furthermore, we incorporate the Gaussian mechanism in both stages to guarantee client-level differential privacy.

Wang, Jiayi [ORNL]↗
DOE OSTI2025

TorchBraid: High-Performance Layer-Parallel Training of Deep Neural Networks with MPI and GPU Acceleration

TorchBraid is a high-performance implementation of layer-parallel training for deep neural networks (DNNs) supporting MPI-based parallelism and GPU acceleration. Layer-parallel training has been developed to overcome the serialization inherent in forward and backward propagation of DNNs that limits utilization of computational resources in the strong scaling limit. To achieve this, TorchBraid integrates the PyTorch neural network framework with the state-of-the-art XBraid time-parallel library. Furthermore, this article presents the use and performance of TorchBraid, in addition to solutions for overcoming the algorithmic challenges inherent in combining automatic differentiation with layer-parallel. Results are presented with and without GPU acceleration for the Tiny ImageNet and MNIST image classification data sets, as well as recurrent neural networks. Overall, TorchBraid enables fast training of DNNs, both in a strong and weak scaling context. In addition to the TorchBraid software, several new advances in applying layer-parallel algorithms are detailed. Integration of layer-parallel with data-parallel algorithms is presented for the first time, showing the computational advantages of the combination. Standard deep learning techniques, like batch-normalization, are developed for layer-parallel training. Finally, a new approach combining layer-parallel with spatial coarsening in order to accelerate training for 3D image classification shows roughly a 10× speedup over serial execution.

Layer-parallel↗
DOE OSTI2024

Hyperparameter Studies for Vision Transformers Trained on High-Fidelity Simulations

This library is a collection of python modules that define, train, and analyze vision-transformer (ViT) machine learning models. The code implements, with mild modifications, ViT models that have been made publicly available through publication and GitHub code. The training data for these models is hydrodynamic simulation output in the form of numpy arrays. This library contains code to train these ViT models on the hydrodynamic simulation output with a variety of hyperparameters, and to compare the results of such models. Furthermore, the library contains definitions of simple convolutional neural network (CNN) machine learning architectures which can be trained on the same hydrodynamic simulation output. These are included as a reference point to compare the ViT models to. Additionally, the library includes trained ViT and CNN models and example input data for demonstration purposes. The code is based on the PyTorch python library.

Callis, Skylar↗
DOE OSTI2023

Machine learning-based inversion for acoustic impedance with large synthetic training data: Workflow and data characterization

Where wells are sparse or training data are difficult to label with high-quality wireline-derived impedance logs, machine learning (ML)-based inversion of acoustic impedance typically depends on small training data sets, leading to biased prediction. We have advanced a novel workflow that applies large synthetic seismic training data to reduce facies-related bias. Using a geologically realistic model as the truth model, we randomly select sparse seed wells to perform sequential Gaussian simulation (SGS) for impedance models of the same geometry and simulate facies variability. We implement random forest regression on 30 features extracted from the synthetic volume. We observe that more seed wells tend to reduce facies-induced bias by sampling more types of facies, resulting in a better prediction. We then focus on the responses of SGS models to facies changes, the number of seed wells necessary for a useful synthetic model, and how much a synthetic model can help ML-based inversion. Here, we observe that the SGS synthetic training model outperforms well-direct training in general. For modeled clastic shore-zone systems in Miocene Gulf of Mexico, two or more seed wells are necessary for a significant reduction of root-mean-square error and outliners, and improvement of facies imaging. In a field-data test, we apply a similar workflow to quantitatively predict acoustic impedance, which is then converted to a sand-volume map at a high-frequency sequence (10–100 m), revealing detailed facies and sandstone patterns. Such results are valuable in many geologic and engineering applications, such as hydrocarbon and CO 2 reservoir prospecting, reserve estimation, simulation, etc.

3D seismic↗
DOE OSTI2020

Gen IV Education and Training Working Group Webinars’ Initiative

Collaboration and support among national laboratories, industry, universities, and research and development organizations are vital to not only maintain a skilled and competent nuclear workforce but also to avert the risk of human resource shortages. As stated in a recent IAEA paper [1], the world nuclear electrical generating capacity is projected to increase to 554 GW(e) by 2030 and up to 874 GW(e) by 2050 (Fig. 1). This represents a 42% increase over current levels by 2030 and a doubling of the current capacity by 2050. To promote Education and Training (E&T) on Gen IV reactor systems and other nuclear related topics of interest, the Gen IV Education and Training Working Group (ETWG) identifies and advertises training courses; engages collaboration with other international education and training organizations; delivers webinars dedicated to Gen IV systems; and maintains a modern social medium platform to exchange information and ideas on Gen IV R&D topics, as well as on related GIF education and training activities. At the end of June 2020, the GIF ETWG has produced, podcasted and posted forty-one webinars covering the six Gen IV systems and various subjects addressing e.g. the economics of the nuclear fuel cycle, sustainability aspects of Gen IV systems, nuclear fuels and materials challenges, the thorium fuel cycle, energy conversion systems, and lessons learned for knowledge management and preservation. This paper describes the development of these webinars from the initial concept to its full realization, with future webinars planned in 2021, addressing topics such as materials and fuels performance for advanced reactors, small modular reactor.

Paviet, Patricia D.↗