Search NASA⌕ Search

SEARCH · Search NASA

Results for “Trainability”

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.

32 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

A Two-Stage Quantum Reinforcement Learning Method for Multi-Objective Transmission Switching

Multi-objective transmission switching (MO-TS) problems involve the strategic reconfiguration of network topology to simultaneously optimize multiple objectives. As the system scale increases, finding feasible solutions becomes increasingly challenging due to the problem's nonlinearity and high computational complexity. To address these challenges, this paper proposes a two-stage quantum reinforcement learning method that leverages potential quantum advantages for MO-TS. In the first stage, candidate switching lines are identified using a graph-theoretical approach to reduce the problem's dimensionality. The second stage introduces a quantum-classical reinforcement learning framework, where a learnable measurement-based CNN-ResVQC architecture is developed to effectively reduce the input dimension for quantum processing, mitigate vanishing gradients, and enhance trainability while improving the quantum circuit's flexibility in modeling complex decision policies for MO-TS. Numerical studies on IEEE 14-bus, 57-bus, and 118-bus systems demonstrate that the proposed algorithm achieves superior training stability and faster convergence with approximately 1% of the network parameters required by classical algorithms, highlighting its effectiveness, efficiency, and scalability. Furthermore, the practicality is validated through its stable convergence under three common quantum noise channels.

99 GENERAL AND MISCELLANEOUS↗
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

Intercomparison of Deep Learning Model Architectures for Atmospheric River Prediction

With a rapid surge in the application of machine learning (ML) for a diverse range of tasks in climate science, the present study addresses a challenge for climate scientists when selecting the optimal ML or deep learning (DL) architecture for a given application. In particular, a DL intercomparison study was performed with a focus on forecasting the position of atmospheric rivers (ARs) on short-range time scales (up to 5-day lead times). AR predictions from multiple DL architectures, including various types of convolutional autoencoders and a vision transformer (ViT), were compared against ECMWF ERA5 reanalysis and hindcasts from a global climate model. DL models with similar trainable parameters were trained on ERA5 reanalysis data and AR positions derived from a thresholding algorithm to ensure a fair comparison among the DL models. Each model’s performance and accuracy in forecasting AR location and key input fields within a 5-day window were assessed using metrics of root-mean-square error, anomaly correlation, and mean intersection over union. The ViT architecture outperformed other autoencoder models in most of the metrics. Incorporating additional meteorological fields only yielded slight improvements in forecasting certain fields at longer lead times. The results also suggest that a smaller number of input time steps or smaller number of autoregressive steps can achieve better prediction skills, while also improving the overall computational efficiency. This research offers valuable insights into the strengths and weaknesses of different DL techniques for AR forecasting, hopefully guiding the development of improved models for forecasting this phenomenon.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Development of message passing-based graph convolutional networks for classifying cancer pathology reports

Abstract Background Applying graph convolutional networks (GCN) to the classification of free-form natural language texts leveraged by graph-of-words features (TextGCN) was studied and confirmed to be an effective means of describing complex natural language texts. However, the text classification models based on the TextGCN possess weaknesses in terms of memory consumption and model dissemination and distribution. In this paper, we present a fast message passing network (FastMPN), implementing a GCN with message passing architecture that provides versatility and flexibility by allowing trainable node embedding and edge weights, helping the GCN model find the better solution. We applied the FastMPN model to the task of clinical information extraction from cancer pathology reports, extracting the following six properties: main site, subsite, laterality, histology, behavior, and grade. Results We evaluated the clinical task performance of the FastMPN models in terms of micro- and macro-averaged F1 scores. A comparison was performed with the multi-task convolutional neural network (MT-CNN) model. Results show that the FastMPN model is equivalent to or better than the MT-CNN. Conclusions Our implementation revealed that our FastMPN model, which is based on the PyTorch platform, can train a large corpus (667,290 training samples) with 202,373 unique words in less than 3 minutes per epoch using one NVIDIA V100 hardware accelerator. Our experiments demonstrated that using this implementation, the clinical task performance scores of information extraction related to tumors from cancer pathology reports were highly competitive.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Improved Subseasonal Forecasting of Extreme Polar Vortices Using Machine Learning

Our research was focused on forecasting the position and shape of the winter stratospheric polar vortex at a subseasonal timescale of 15 days in advance. To achieve this, we employed both statistical and neural network machine learning techniques. The analysis was performed on 42 winter seasons of reanalysis data provided by NASA giving us a total of 6,342 days of data. The state of the polar vortex for determined by using geometric moments to calculate the centroid latitude and the aspect ratio of an ellipse fit onto the vortex. Timeseries for thirty additional precursors were calculated to help improve the predictive capabilities of the algorithm. Feature importance of these precursors was performed using random forest to measure the predictive importance and the ideal number of precursors. Then, using the precursors identified as important, various statistical methods were tested for predictive accuracy with random forest and nearest neighbor performing the best. An echo state network, a type of recurrent neural network that features sparsely connected hidden layer and a reduced number of trainable parameters that allows for rapid training and testing, was also implemented for the forecasting problem. Hyperparameter tuning was performed for each methods using a subset of the training data. The algorithms were trained and tuned on the first 41 years of data, then tested for accuracy on the final year. In general, the centroid latitude of the polar vortex proved easier to predict than the aspect ratio across all algorithms. Random forest outperformed other statistical forecasting algorithms overall but struggled to predict extreme values. Forecasting from echo state network suggested a strong predictive capability past 15 days, but further work is required to fully realize the potential of recurrent neural network approaches.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

SQMS Quantum R&D in Machine Learning, Optimization and Sensing beyond Fundamental Physics Applications

This newly formed team at SQMS under the Ecosystem Thrust is looking to develop capabilities impacting societal advances outside the core domain of HEP and condensed matter physics. We explicitly leverage the experimental and algorithmic innovations developed across all groups as well as connect to broad-scope external projects of the diverse team of PIs. As the inaugural set of projects, we are studying numerically quantum machine learning models inspired by efficiently trainable echo-state and orthogonal neural networks and developing designs for related experiments to be performed on quantum processors based on SQMS SRF cQED technology and Rigetti s transmon arrays. Investigated models exploit ideas and lessons learned from multiple prior work by SQMS team members in a variety of internal and external activities [R1]. Target initial applications include noisy signal processing, potentially captured by quantum sensors or noisy QPUs, as well as simulation and classification of healthcare data. For instance, image reconstruction of the brain s electrical properties by solving the inverse Maxwell equation problem with uncertainty [R2] through a hybrid quantum-classical physics-informed architecture for time-dependent processes [R3]. The group is also investigating the application and development of novel quantum sensors based on magnetic levitation of a superconducting sphere coupled to a superconducting qubit. This coupling enables high-precision measurements of the position of the sphere, which can be used for sensitive detection of forces, enabling practical applications such as gravimetry for geophysics analysis, or accelerometry for GPS-denied navigation [R4] [R1] Rieffel, Eleanor G., Ata Akbari Asanjan, M. Sohaib Alam, Namit Anand, David E. Bernal Neira, Sophie Block, Lucas T. Brady et al. "Assessing and advancing the potential of quantum computing: A NASA case study." Future Generation Computer Systems (2024). [R2] Yu, X., Serrall s, J.E., Giannakopoulos, I.I., Liu, Z., Daniel, L., Lattanzi, R. and Zhang, Z., 2023. Pifon-ept: Mr-based electrical property tomography using physics-informed fourier networks. IEEE Journal on Multiscale and Multiphysics Computational Techniques. [R3] Wudarski, Filip, Daniel OConnor, Shaun Geaney, Ata Akbari Asanjan, Max Wilson, Elena Strbac, P. Aaron Lott, and Davide Venturelli. "Hybrid quantum-classical reservoir computing for simulating chaotic systems." arXiv preprint arXiv:2311.14105 (2023). [R4] Higgins, Gerard, Saarik Kalia, and Zhen Liu. "Maglev for dark matter: Dark-photon and axion dark matter sensing with levitated superconductors." Physical Review D 109.5 (2024): 055024.

Venturelli, Davide↗
DOE OSTI2024

Continuous integration data-driven platform of industrial-scale subsurface storage for real-time analytics

This project helped address the growing need for efficient and scalable models to support geological carbon and energy storage, which are crucial for achieving net-zero emissions. Traditionally accurate high-fidelity numerical models have been used to simulate relevant storage processes under a handful of processes, however such models are computationally demanding, making uncertainty quantification impractical. Consequently, we first developed a machine learning framework, based on Graph Neural Operators (GNOs), to improving the accuracy of model predictions for a fixed computational budget. We then developed an Ensemble of Improved Neural Operators (ENO), which uses bagging and Monte Carlo dropout techniques, to further improve prediction accuracy. Lastly, we developed the way to explain progressive transfer learning methods to reduce the amount of training data and computational cost of training (i.e., reduce trainable parameters) when using our models for multiple storage sites. Our numerical investigation, which used real-world case studies, demonstrated that our framework can significantly improve the safety and efficiency of geological storage operations, with potential applications in other domains such as geothermal reservoirs and climate modeling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Unrolled Video Super-Resolution Network with Autoregressive Prior for the Case of Known Motion

Real-time detection and classification of distant objects is necessary for many national security applications. However, when objects are far from the sensor, they occupy only a small number of pixels in the captured video, limiting the amount of visual detail available for recognition. State-of-the-art classification methods typically rely on high-resolution (HR) video streams to capture characteristic object features, but obtaining such detail is challenging for distant objects that occupy only a few pixels. This motivates the development of video super-resolution (VSR) methods that enhance object classification by recovering fine details from low-pixel representations. Current VSR methods rely either on model-based optimization, which is interpretable but computationally expensive, or on learning-based approaches, which are efficient and high-performing but often lack flexibility and interpretability. In this report, we propose an end-to-end trainable unrolled VSR network, UVSRNet, which super-resolves each frame in a video by exploiting sub-pixel motion between neighboring low-resolution (LR) frames as well as incorporating high-frequency detail from previously super-resolved frames. In particular, by unrolling a plug-and-play (PnP) half-quadratic splitting (HQS) algorithm, we leverage a model-based data-fitting module alongside a learning-based autoregressive prior module. This combination yields a method that maintains the flexibility and interpretability of model-based methods while achieving the performance advantages of learning-based methods.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2025

CRCNS22 Learning Rules in the Hippocampus and their Mapping to Neuromorphic Systems (Final Technical Report)

Large scale biologically-realistic computational models are key to investigating the interplay between structure and function in nervous systems, thus paving the way to new clinical methods and neuro-inspired computing solutions. This project focuses on the hippocampus, in particular the CA3-CA1 regions, due to their role in associative learning and memory, pattern separation and completion, and spatial navigation. Investigations into the neuronal organization and learning rule(s) of this circuit can shed light into how declarative memories are formed, stored, recalled and forgotten and inform computational, experimental and clinical neuroscience work. Our project aims at developing a novel data-driven methodology supported by a broad heterogeneous base of neuroscience experimental knowledge and inspired from advances in computer science and engineering. Specifically, this work will benchmark existing and new learning rules within a full-scale spiking neural network simulation of the CA3-CA1 region. The model will be based on an open-source repository, called the Hippocampome, which contains neuronal morphologies, firing patterns, synapse probabilities, and most other required parameters for all known neuron types in the rodent hippocampal formation. The model will be first trained in a supervised fashion for associative memory tasks using backpropagation through time traditionally used in computer science, enhanced with a new technique called the surrogate gradient method. This optimization method will be used to obtain a global loss minimization, but it is not biologically inspired as it assumes the use of data not locally available to the synapses. However, we propose its use as a benchmarking tool, to compare the training performance of local biologically plausible and hardware-mappable learning rules at scale. New rules or combinations will be proposed and tested as needed, based on the obtained results. Progress in this area will also drive the development of novel hardware-mappable algorithms for continual lifelong learning and categorization of new events from few presented examples. This project goes beyond the existing state-of-the-art by looking at large scale realistic neuronal circuits as networks trainable via global optimization methods such as surrogate gradient descent. The objective function of the brain that supports learning is largely unknown, but it is likely that it operates through local learning rules. Studying network trajectories around local minima as proposed in this work represents a useful strategy for understanding whether a network is training by using a specific (set of) learning rule(s). Starting from a completely untrained network is a challenging test since it is difficult to determine how the learning rule affects the trajectory of the network. This interdisciplinary project will help understand what rule governs learning in these regions or if multiple learning rules are involved. The work will develop a robust methodology to measure if the network is converging to the target solution, oscillating around it, or diverging away.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations

Addressing the "Red-AI" trend of rising energy consumption by large-scale neural networks, this study investigates the measured energy consumption of training various fully connected neural network architectures. We introduce the BUTTER-E dataset, an augmentation to the BUTTER Empirical Deep Learning dataset, containing energy consumption and performance data from 41,129 individual experimental runs spanning 30,582 distinct configurations: 13 datasets, 20 sizes (trainable parameters), 8 "shapes", and 14 depths on both CPUs and GPUs using node-level watt-meters. This dataset reveals the complex relationship between dataset size, network structure, and energy use. Our analysis uncovers a surprising, hardware-mediated non-linear relationship between energy efficiency and network design, challenging the assumption that reducing the number of parameters or FLOPs is the best way to achieve greater energy efficiency. We propose a straightforward and effective energy model that accounts for network size, computing, and memory hierarchy. Highlighting the need for cache-considerate algorithm development, we suggest a codesign approach to energy efficient network, algorithm, and hardware design. This work contributes to the fields of sustainable computing and Green AI, offering practical guidance for creating more energy-efficient neural networks and promoting sustainable AI.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Enhancing Lattice Kinetic Schemes for Fluid Dynamics with Lattice-Equivariant Neural Networks

A new class of equivariant neural networks is presented, hereby dubbed lattice-equivariant neural networks (LENNs), designed to satisfy local symmetries of a lattice structure. The approach develops within a recently introduced framework aimed at learning neural network-based surrogate models’ lattice Boltzmann collision operators. Whenever neural networks are employed to model physical systems, respecting symmetries and equivariance properties has been shown to be key for accuracy, numerical stability, and performance. Here, hinging on ideas from group representation theory, trainable layers are defined whose algebraic structure is equivariant with respect to the symmetries of the lattice cell. In this work, the presented method naturally allows for efficient implementations, in terms of both memory usage and computational costs, supporting scalable training/testing for lattices in two spatial dimensions and higher (in which the size of symmetry group grows). The approach is validated and tested considering 2D and 3D flowing dynamics, both in laminar and turbulent regimes. It is compared with group-averaged-based symmetric networks and with plain, nonsymmetric, networks, showing how the presented approach unlocks the (a posteriori) accuracy and training stability of the former models and the train/inference speed of the latter networks. (LENNs are about one order of magnitude faster than group-averaged networks in 3D.) The work in this paper opens toward practical use of machine learning-augmented lattice Boltzmann CFD in real-world simulations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Data Quality Monitoring for the Hadron Calorimeters Using Transfer Learning for Anomaly Detection

The proliferation of sensors brings an immense volume of spatio-temporal (ST) data in many domains, including monitoring, diagnostics, and prognostics applications. Data curation is a time-consuming process for a large volume of data, making it challenging and expensive to deploy data analytics platforms in new environments. Transfer learning (TL) mechanisms promise to mitigate data sparsity and model complexity by utilizing pre-trained models for a new task. Despite the triumph of TL in fields like computer vision and natural language processing, efforts on complex ST models for anomaly detection (AD) applications are limited. In this study, we present the potential of TL within the context of high-dimensional ST AD with a hybrid autoencoder architecture, incorporating convolutional, graph, and recurrent neural networks. Motivated by the need for improved model accuracy and robustness, particularly in scenarios with limited training data on systems with thousands of sensors, this research investigates the transferability of models trained on different sections of the Hadron Calorimeter of the Compact Muon Solenoid experiment at CERN. The key contributions of the study include exploring TL’s potential and limitations within the context of encoder and decoder networks, revealing insights into model initialization and training configurations that enhance performance while substantially reducing trainable parameters and mitigating data contamination effects.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Exponential concentration in quantum kernel methods

Kernel methods in Quantum Machine Learning (QML) have recently gained significant attention as a potential candidate for achieving a quantum advantage in data analysis. Among other attractive properties, when training a kernel-based model one is guaranteed to find the optimal model’s parameters due to the convexity of the training landscape. However, this is based on the assumption that the quantum kernel can be efficiently obtained from quantum hardware. In this work we study the performance of quantum kernel models from the perspective of the resources needed to accurately estimate kernel values. We show that, under certain conditions, values of quantum kernels over different input data can be exponentially concentrated (in the number of qubits) towards some fixed value. Thus on training with a polynomial number of measurements, one ends up with a trivial model where the predictions on unseen inputs are independent of the input data. We identify four sources that can lead to concentration including expressivity of data embedding, global measurements, entanglement and noise. For each source, an associated concentration bound of quantum kernels is analytically derived. Lastly, we show that when dealing with classical data, training a parametrized data embedding with a kernel alignment method is also susceptible to exponential concentration. Our results are verified through numerical simulations for several QML tasks. Altogether, we provide guidelines indicating that certain features should be avoided to ensure the efficient evaluation of quantum kernels and so the performance of quantum kernel methods.

97 MATHEMATICS AND COMPUTING↗