Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Neural Networks (Computer)”

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 829 records · Page 46

Introduction: Neuromorphic Materials

The explosive growth in data collection and the need to process it efficiently, as well as the desire to automate increasingly complex tasks in transportation, medical care, manufacturing, security and many other fields have motivated a growing interest in neuromorphic computing. Unlike the binary, transistorbased ON/OFF logic gates and separate logic and memory functionalities employed in digital computing, neuromorphic computing is inspired by animal brains that use interconnected synapses and neurons to perform processing, storage and transmission of information at the same location, while only consuming ~20 W or less of power. Motivated by the brain’s efficiency, adaptability, self-learning and resiliency qualities, neuromorphic computing can be broadly defined as an approach to processing and storing information using hardware and algorithms inspired by models of biological neural systems. Present research in neuromorphic computing encompasses approaches that vary significantly in their degree of neuro-inspiration, from systems that only incorporate features such as asynchronous, event-driven operation or use crossbar arrays of non-volatile memory (NVM) elements to accelerate deep neural networks (DNNs), to designs that embrace the extreme parallelism, sparsity, reconfigurability, adaptability, complexity and stochasticity observed in nervous systems. The term ‘neuromorphic’ computing is often credited to Carver Mead, who in the 1980s investigated Si-based analog electronics to replicate functions of the animal retina. Earlier important advances in this field include the work of Frank Rosenblatt, who proposed the concept of the perceptron, Bernard Widrow, who used this concept to build one of the first analog neural networks, the Adaline and many other researchers (see ref. 6 for an historical perspective on neuromorphic computing). With the recent increase in the use of artificial intelligence and large language models, and rising concerns over the associated energy costs, interest in neuromorphic hardware has expanded rapidly. According to some estimates, driven largely by the drastic growth in the training use of artificial intelligence (AI) models using the current computing architectures, the energy cost of computing is projected to reach the energy supply worldwide by 2045. Furthermore, while this is not a realistic outcome, it means that, if more efficient computing technologies are not developed -- soon -- the world will soon become one where demand for energy and market constraints limit the continued increase of societal access to AI and cloud services from data centers. Data centers used for training and use of these models consume hundreds of terawatt hours of electricity, already past 4% of the US electricity demand.

Circuits↗

A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks

To fit sparse linear associations, a LASSO sparsity inducing penalty with a single hyperparameter provably allows to recover the important features (needles) with high probability in certain regimes even if the sample size is smaller than the dimension of the input vector (haystack). More recently learners known as artificial neural networks (ANN) have shown great successes in many machine learning tasks, in particular fitting nonlinear associations. Small learning rate, stochastic gradient descent algorithm and large training set help to cope with the explosion in the number of parameters present in deep neural networks. Yet few ANN learners have been developed and studied to find needles in nonlinear haystacks. Driven by a single hyperparameter, our ANN learner, like for sparse linear associations, exhibits a phase transition in the probability of retrieving the needles, which we do not observe with other ANN learners. To select our penalty parameter, we generalize the universal threshold of Donoho and Johnstone (Biometrika 81(3):425–455, 1994) which is a better rule than the conservative (too many false detections) and expensive cross-validation. In the spirit of simulated annealing, we propose a warm-start sparsity inducing algorithm to solve the high-dimensional, non-convex and non-differentiable optimization problem. We perform simulated and real data Monte Carlo experiments to quantify the effectiveness of our approach.

97 MATHEMATICS AND COMPUTING↗

Machine Learning for Scalable and Optimal Load Shedding Under Power System Contingency

Prompt and effective corrective actions in response to unexpected contingencies are crucial for improving power system resilience and preventing cascading blackouts. The optimal load shedding (OLS) accounting for network limits has the potential to address the diverse system-wide impacts of contingency scenarios as compared to traditional local schemes. However, due to the fast cascading propagation of initial contingencies, real-time OLS solutions are challenging to attain in large systems with high computation and communication needs. In this paper, we propose a decentralized design that leverages offline training of a neural network (NN) model for individual load centers to autonomously construct the OLS solutions from locally available measurements. Our learning-for-OLS approach can greatly reduce the computation and communication needs during online emergency responses, thus preventing the cascading propagation of contingencies for enhanced power grid resilience. Numerical studies on both the IEEE 118-bus system and a synthetic Texas 2000-bus system have demonstrated the efficiency and effectiveness of our scalable OLS learning design for timely power system emergency operations.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Evaluating the Use of Foundational Chemical Language Models in Multimodal Graph Fusion

Rapid and accurate prediction of the physicochemical properties of molecules given their structures remains a key challenge in cheminformatics. Machine learning approaches offer high-throughput options, but the optimality of inductive biases and data representations are up for debate. For example, BERT-based masked language models (MLMs) can be trained in a self-supervised way on hundreds of millions to billions of readily available SMILES strings. Another option is graph neural networks (GNNs), which can operate directly on molecular structures. Yet, generating accurate molecular geometry is computationally expensive, leading to a relative scarcity in data compared to SMILES strings. It is attractive to combine these two paradigms by pre-training an LM on a large corpus of SMILES strings and embedding these representation into a geometric graph neural network. Despite the promise of such an approach, and contrary to previous studies, we find mixed results with the combination of the LMs and GNNs on several molecule datasets. In particular, we found evidence for improvement on the FreeSolv and QM7 benchmarks, but degraded performance on the ESOL, LIPO and QM9 datasets compared to a GNN baseline.

Francel, Collin [University of Alabama]↗

Optimizing deep learning hyper-parameters through an evolutionary algorithm. In: MLHPC '15 Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments, Article No. 4

There has been a recent surge of success in utilizing Deep Learning (DL) in imaging and speech applications for its relatively automatic feature generation and, in particular for convolutional neural networks (CNNs), high accuracy classification abilities. While these models learn their parameters through data-driven methods, model selection (as architecture construction) through hyper-parameter choices remains a tedious and highly intuition driven task. To address this, Multi-node Evolutionary Neural Networks for Deep Learning (MENNDL) is proposed as a method for automating network selection on computational clusters through hyper-parameter optimization performed via genetic algorithms.

Young, Steven R.↗

Machine Learning Surrogates of a Fuel Matrix Degradation Process Model for Performance Assessment of a Nuclear Waste Repository

Spent nuclear fuel repository simulations are currently not able to incorporate detailed fuel matrix degradation (FMD) process models due to their computational cost, especially when large numbers of waste packages breach. The current paper uses machine learning to develop artificial neural network and k-nearest neighbor regression surrogate models that approximate the detailed FMD process model while being computationally much faster to evaluate. Further, using fuel cask temperature, dose rate, and the environmental concentrations of CO 3 2- , O 2 , Fe 2+ , and H 2 as inputs, these surrogates show good agreement with the FMD process model predictions of the UO 2 degradation rate for conditions within the range of the training data. A demonstration in a full-scale shale repository reference case simulation shows that the incorporation of the surrogate models captures local and temporal environmental effects on fuel degradation rates while retaining good computational efficiency.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Plateau Phenomenon in Gradient Descent Training of RELU Networks: Explanation, Quantification, and Avoidance

The ability of neural networks to provide ‘best in class’ approximation across a wide range of applications is well-documented. Nevertheless, the powerful expressivity of neural networks comes to naught if one is unable to effectively train (choose) the parameters defining the network. In general, neural networks are trained by gradient descent type optimization methods,a stochastic variant thereof. In practice, such methods result in the loss function decreases rapidly at the beginning of training but then, after a relatively small number of steps, significantly slow down. The loss may even appear to stagnate over the period of a large number of epochs, only to then suddenly start to decrease fast again for no apparent reason. This so-called plateau phenomenon manifests itself in many learning tasks. The present work aims to identify and quantify the root causes of plateau phenomenon.analysis is carried out in the setting of univariate ReLU networks. No assumptions are made on the number of neurons relative to the number of training data, and our results hold for both the lazy and adaptive regimes. Here, the main findings are: plateaux correspond to periods during which activation patterns remain constant, where activation pattern refers to the number of data points that activate a given neuron; quantification of convergence of the gradient flow dynamics; and, characterization stationary points in terms solutions of local least squares regression lines over subsets of the training data. Based on these conclusions, we propose a new iterative training method, the Active Neuron Least Squares (ANLS), characterised by the explicit adjustment of the activation pattern at each step, which is designed to enable a quick exit from a plateau. Illustrative numerical examples are included throughout.

97 MATHEMATICS AND COMPUTING↗

Modelling of a Flow-Induced Oscillation, Two-Cylinder, Hydrokinetic Energy Converter Based on Experimental Data

The VIVACE Converter consists of cylindrical oscillators in tandem subjected to transverse flow-induced oscillations (FIOs) that can be improved by varying the system parameters for a given in-flow velocity: damping, stiffness, and in-flow center-to-center spacing. Compared to a single isolated cylinder, tandem cylinders can harness more hydrokinetic energy due to synergy in FIO. Experimental and numerical methods have been utilized to analyze the FIO and energy harnessing of VIVACE. A surrogate-based model of two tandem cylinders is developed to predict the power harvesting and corresponding efficiency by introducing a backpropagation neural network. It is then utilized to reduce excessive experimental or computational testing. The effects of spacing, damping, and stiffness on harvested power and efficiency of the established prediction-model are analyzed. At each selected flow velocity, optimization results of power harvesting using the prediction-model are calculated under different combinations of damping and stiffness. The main conclusions are: (1) The surrogate model, built on extensive experimental data for tandem cylinders, can predict the cylinder oscillatory response accurately. (2) Increasing the damping ratio range from 0–0.24 to 0–0.30 is beneficial for improving power efficiency, but has no significant effect on power harvesting. (3) In galloping, a spacing ratio of 1.57 has the highest optimal harnessed power and efficiency compared with other spacing values. (4) Two tandem cylinders can harness 2.01–4.67 times the optimal power of an isolated cylinder. In addition, the former can achieve 1.46–4.01 times the efficiency of the latter. (5) The surrogate model is an efficient predictive tool defining parameters of the Converter for improved energy acquisition.

backpropagation neural network↗

Breaking the curse of dimensionality: Solving configurational integrals for crystalline solids by tensor networks

Accurately evaluating configurational integrals for dense solids remains a central and difficult challenge in the statistical mechanics of condensed systems. Here, we present a tensor network approach that reformulates the high-dimensional configurational integral for identical-particle crystals into a sequence of computationally efficient summations. We represent the integrand as a high-dimensional tensor and apply tensor-train (TT) decomposition together with a custom TT-cross interpolation. This approach circumvents the need to explicitly construct the full tensor. We introduce tailored rank-1 and rank-2 schemes optimized for sharply peaked Boltzmann probability densities, typical for identical-particle crystals. When applied to the calculation of internal energy and pressure-temperature curves for crystalline Cu and Ar at high (GPa) pressures, as well as the alpha-to-beta phase transition diagram of Sn, our method accurately reproduces molecular dynamics simulation results using tight-binding, machine learning, hierarchical interacting particle–neural network, and modified embedded atom method potentials,all within seconds of computation time.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction

In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min-Max technique to initialize the k-center of the RRBF neural network. The k-means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k-means algorithm are then boosted by the Fuzzy Min-Max technique.

97 MATHEMATICS AND COMPUTING↗

Communication: Separable potential energy surfaces from multiplicative artificial neural networks

We present a potential energy surface fitting scheme based on multiplicative artificial neural networks. It has the sum of products form required for efficient computation of the dynamics of multidimensional quantum systems with the multi configuration time dependent Hartree method. Moreover, it results in analytic potential energy matrix elements when combined with quantum dynamics methods using Gaussian basis functions, eliminating the need for a local harmonic approximation. Scaling behavior with respect to the complexity of the potential as well as the requested accuracy is discussed.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Development of a neural network model for peeling–ballooning stability analysis in the KSTAR tokamak pedestals

The neural network model, MISHKA-NN is developed to mitigate the computational burden associated with the linear ideal magnetohydrodynamic (MHD) stability analysis of the pedestal based on the peeling–ballooning (P–B) model. By utilizing both 1D plasma profiles (current density, pressure gradient, and safety factor) and 0D parameters (plasma geometry, total current, and toroidal mode number), the model predicts linear growth rate of edge-localized ideal MHD instability in a given equilibrium state. By enabling the prediction of each instability within a second, the model reduces the time required for plotting a pedestal P–B stability diagram (j - α diagram) from approximately 100 CPU hours to a few CPU minutes. Notably, even with the utilization of parametric pressure and current profiles and plasma boundary shapes for the training dataset, the model shows a satisfactory level of performance in benchmarking the j - α diagram for the reconstructed equilibrium from a KSTAR tokamak experiment. We anticipate the model to serve as a versatile alternative to 2D linear MHD stability codes, alleviating numerical costs.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Deep Image Prior Enabled Full Waveform Inversion (Final Technical Report)

MS Student Naveen Gupta worked on the problem of full waveform inversion (FWI) using neural networks as shown in Figure 1. Our goal was to learn a neural network to represent the subsurface velocity model, which when fed into the FWI module (implemented using a numerical forward model of wave equations) produces amplitude estimates that match with ground-truth observations of amplitude. We used neural networks to solve the inverse problem of estimating velocity distributions for a given seismic amplitude data such that, once trained, our neural network model can generate a distribution of velocity profiles for different random vectors fed as inputs to the neural network model.

97 MATHEMATICS AND COMPUTING↗

ELM: AN ALGORITHM TO ESTIMATE THE ALPHA ABUNDANCE FROM LOW-RESOLUTION SPECTRA

We have investigated a novel methodology using the extreme learning machine (ELM) algorithm to determine the α abundance of stars. Applying two methods based on the ELM algorithm—ELM+spectra and ELM+Lick indices—to the stellar spectra from the ELODIE database, we measured the α abundance with a precision better than 0.065 dex. By applying these two methods to the spectra with different signal-to-noise ratios (S/Ns) and different resolutions, we found that ELM+spectra is more robust against degraded resolution and ELM+Lick indices is more robust against variation in S/N. To further validate the performance of ELM, we applied ELM+spectra and ELM+Lick indices to SDSS spectra and estimated α abundances with a precision around 0.10 dex, which is comparable to the results given by the SEGUE Stellar Parameter Pipeline. We further applied ELM to the spectra of stars in Galactic globular clusters (M15, M13, M71) and open clusters (NGC 2420, M67, NGC 6791), and results show good agreement with previous studies (within 1σ). A comparison of the ELM with other widely used methods including support vector machine, Gaussian process regression, artificial neural networks, and linear least-squares regression shows that ELM is efficient with computational resources and more accurate than other methods.

79 ASTRONOMY AND ASTROPHYSICS↗

FPGA-Accelerated Machine Learning Inference as a Service for Particle Physics Computing

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave by Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) ms with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600–700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗