Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “neuronal network”

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 OSTI2023

Editorial: Functional microcircuits in the brain and in artificial intelligent systems

Fundamental principles underlying higher-order cognitive functions remain elusive, but recent breakthroughs in neurophysiology and deep learning offer new perspectives. First, experimental studies have uncovered neural circuit motifs consisting of various neuron types; see Brain Initiative Cell Census Network (https://www.nature.com/collections/cicghheddj). For example, inhibitory neuron types expressing exclusive genes have specific targets and distinct functions (Pfeffer et al., 2013). Furthermore, diverse neuron types in cortex and their connectomes were identified in cortical columns (Jiang et al., 2015); see also Barth et al. (2016) for a debate on neuron types. Second, artificial neural networks were originally inspired by structures of the brain (McCulloch and Pitts, 1943) and could be trained to perform complex functions similar to human perception/cognition by deep learning (DL) (Lecun et al., 2015).

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Direct NeTS sampling of nuclear graphite $S(α, β, T)$ in Serpent

For advanced reactor applications, Neural Thermal Scattering (NeTS) modules were developed to predict the thermal scattering law (TSL or $S(α, β, T)$) of a nuclear graphite neutron moderator. NeTS are multi-layer, feedforward artificial neural networks, which act as universal function approximators designed for TSL datasets. In this case, a 4-layer neural network with 164 neurons per layer is trained using FLASSH evaluated data in PyTorch and serialized as a torchscript dictionary to predict $S(α, β, T)$ on-the-fly. Relative, absolute and maximum percent deviations of NeTS from File 7 data generated using the FLASSH code are on the order of 0.01%, 0.1% and 1%, respectively, with low inference latencies of 0.000172 s per $S(α, β, T)$ at a given temperature. Capturing the full dimensionality of possible inelastic neutron-lattice interactions, NeTS functionality is embedded in the Serpent Monte Carlo code, where $S(α, β, T)_{NeTS}$ sampling is conducted on-the-fly and compared to ACE look-up-tables for predicting TREAT criticality. k-eff differences between sampling algorithms of 6 pcm are observed and are within the order of Monte Carlo uncertainty. Compared to discrete and continuous-energy ACE files (30 MB and 131 MB per temperature), the NeTS format is on the order of 200–300 kB for a continuous-temperature, interpolation-free representation of $S(α, β, T)$ and cross sections. NeTS-in-Serpent runtimes comparable with ACE look-up tables are achieved by scaling NeTS for high performance computing architectures with hybrid OpenMP + MPI parallelization. This work validates a novel, self-contained reactor physics framework for predictive cross sections, and demonstrates a general methodology for embedding modern machine learning libraries within existing neutronic analysis frameworks.

Nuclear Criticality Safety Program (NCSP)↗
DOE OSTI2025

From disorganized data to emergent dynamic models: Questionnaires to partial differential equations

Starting with sets of disorganized observations of spatially varying and temporally evolving systems, obtained at different (also disorganized) sets of parameters, we demonstrate the data-driven derivation of parameter dependent, evolutionary partial differential equation (PDE) models capable of generating the data. This tensor type of data is reminiscent of shuffled (multidimensional) puzzle tiles. The independent variables for the evolution equations (their “space” and “time”) as well as their effective parameters are all emergent , i.e. determined in a data-driven way from our disorganized observations of behavior in them. We use a diffusion map based questionnaire approach to build a smooth parametrization of our emergent space/time/parameter space for the data. This approach iteratively processes the data by successively observing them on the “space,” the “time” and the “parameter” axes of a tensor. Once the data become organized, we use machine learning (here, neural networks) to approximate the operators governing the evolution equations in this emergent space. Our illustrative examples are based (i) on a simple advection–diffusion model; (ii) on a previously developed vertex-plus-signaling model of Drosophila embryonic development; and (iii) on two complex dynamic network models (one neuronal and one coupled oscillator model) for which no obvious smooth embedding geometry is known a priori. This allows us to discuss features of the process like symmetry breaking, translational invariance, and autonomousness of the emergent PDE model, as well as its interpretability.

generative models↗
DOE OSTI2023

Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation

Graph convolutional networks leverage both graph structures and features on nodes and edges for improved learning performance in comparison with classical machine learning approaches. Spiking neuromorphic computers natively implement network-like computation and have been shown to be successful at implementing graph learning without features. Incorporating graph features brings the challenge of efficient feature representation and balancing the contribution of topology and features in learning. In this work, we present our design of a simulated network of spiking neurons to perform semi-supervised learning on graph data using both the graph structure and the node features. We explore various design choices, present preliminary results, and discuss the opportunities for using neuromorphic computers for this task in the future.

Cong, Guojing↗
DOE OSTI2026

Knowledge gaps for neuromorphic ionic computing

BACKGROUND Neuromorphic computing, inspired by the human brain’s ability to process information efficiently, represents a transformative approach to computation. In this Review, we explore the emerging field of neuromorphic ionic computing, which leverages ionic conduction and coupling to mimic neural processes, and identify critical knowledge gaps that must be addressed to realize its full potential. A central theme of the discussion is energy efficiency, a challenge that is both a limitation and an opportunity for this technology. Although complementary metal-oxide semiconductor (CMOS)–based neuromorphic technologies have made strides in scaling to billions of neurons and are increasingly applied in artificial intelligence and numerical computing, they remain orders of magnitude behind the human brain in terms of connectivity and energy efficiency. Neuromorphic ionic computing promises to overcome these limitations by leveraging the distinct architectural and operational principles of the brain. Our brains achieve this energy efficiency by combining several key features: using the same network elements to store and process information; using an incredibly complex and massively interconnected three-dimensional (3D) network of locally active elements that enables sparsity, robustness in the presence of noise, adaptation, and life-long learning; computing at comparatively low voltage and frequency; and last, taking advantage of a plethora of ions and small molecules as information carriers. Here, we propose that ionic computing systems can take advantage of similar features to achieve substantial gains in energy efficiency. ADVANCES Since the first reports of neuromorphic ionic behavior in nanofluidic channels, we have witnessed an explosion of reports that used ionic devices to produce synaptomimetic behaviors. However, achieving the goals of ionic computing requires not only implementation of much more sophisticated device functionality but also overcoming fundamental barriers in materials science, device architecture, and system integration. Current ionic devices, even those incorporating state-of-the-art materials, still suffer from limited functionality and stability, which restrict their performance and increase energy demands. Developing new materials with enhanced ionic properties is essential to overcome these limitations. Similarly, the design of neuromorphic devices must evolve to leverage the particular advantages of ionic processes. Existing architectures often follow a single-information-carrier logic of conventional electronics or are constructed of mesoscale fluidics, failing to capitalize on the energy-efficient mechanisms inherent to ionic systems or implement the multiple-information-carrier paradigm. Current neuromorphic chips focus on large-scale networks of analog memory elements based on mechanisms such as charge trap (flash), filamentary, phase change, or spin, which are built on top of a network of artificial CMOS neurons. Although such prototype networks have achieved impressive performance, it is difficult to envision how they can implement the key features such as massive connectivity, sophisticated plasticity, adaptability, sparsity, and “multichromatic” computing. Although small-scale devices have demonstrated promising results, integrating them, maintaining energy efficiency, and implementing temperature control as systems grow in complexity and size to computationally relevant scale remain major hurdles. Furthermore, interfacing neuromorphic ionic devices with existing computing technologies presents technical and conceptual challenges that will require innovative approaches that combine insights from neuroscience, materials science, and engineering. OUTLOOK Despite these challenges, the potential impact of neuromorphic ionic computing is profound with potential applications ranging from artificial intelligence to robotics and beyond. We also argue that neuromorphic ionic computing systems should not, at least in the beginning, compete with CMOS technologies but rather should focus on applications that require extreme energy efficiency with chemical and/or biological compatibility, such as biomedical applications (for example, brain-computer interfaces), environmental monitoring, and agricultural and food applications. Ultimately, this Review highlights the crucial role of interdisciplinary collaboration in advancing the field. Neuromorphic ionic computing is not merely a technological innovation; it represents a substantial step toward sustainable computation, aligning with the growing demand for energy-conscious solutions in a world that is increasingly reliant on data and computation.

Neuromorphic↗
DOE OSTI2022

Devices and methods for increasing the speed and efficiency at which a computer is capable of modeling a plurality of random walkers using a density method

A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space, wherein the virtual space comprises a plurality of vertices and wherein the different locations are ones of the plurality of vertices. A corresponding set of neurons in a spiking neural network is assigned to a corresponding vertex such that there is a correspondence between sets of neurons and the plurality of vertices, wherein a spiking neural network comprising a plurality of sets of spiking neurons is established. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network, wherein executing includes tracking how many virtual random walkers are at each vertex at a given time increment.

Aimone, James Bradley↗
DOE OSTI2022

Hybrid Quantum-Classical Neural Networks

Deep learning is one of the most successful and far-reaching strategies used in machine learning today. However, the scale and utility of neural networks is still greatly limited by the current hardware used to train them. These concerns have become increasingly pressing as conventional computers are soon expected to approach the physical limitations that will slow their performance improvements in the near future. For these reasons, scientists have begun to explore alternative computing platforms, like quantum computers, for training neural networks. In recent years, variational quantum circuits have emerged as one of the most successful approaches to quantum deep learning on noisy intermediate scale quantum devices. We propose a hybrid quantum-classical neural network architecture where each neuron is a variational quantum circuit. We empirically analyze the performance of this hybrid neural network on a series of binary classification data sets using a simulated IBM universal quantum computer and a state-of-the-art IBM universal quantum computer. On the simulated hardware, we observe that the hybrid neural network achieves around 10% higher classification accuracy and 20% better minimization of the cost function than an individual variational quantum circuit. On the quantum hardware, we observe that each model only performs well when the qubit and gate count is sufficiently small.

Arthur, Davis↗
DOE OSTI2025

Shape Anisotropy-Dependent Leaking in Magnetic Neurons for Bio-Mimetic Neuromorphic Computing

Spiking neural networks seek to emulate biological computation through interconnected artificial neuron and synapse devices. Spintronic neurons can leverage magnetization physics to mimic biological neuron functions, such as integration tied to magnetic domain wall (DW) propagation in a patterned nanotrack and firing tied to the resistance change of a magnetic tunnel junction (MTJ), captured in the domain wall-magnetic tunnel junction (DW-MTJ) device. Leaking, relaxation of a neuron when it is not under stimulation, is also predicted to be implemented based on DW drift as a DW relaxes to a low energy position, but it has not been well explored or demonstrated in device prototypes. Here, in this work, we study DW-MTJ artificial neurons capable of leaky integrate-and-fire (LIF) behavior and demonstrate geometry-dependent leaking dynamics that results in repeatable, tunable LIF operation. Studying the behavior of five different device designs, we show tuning the geometry, stimulating fields and currents, and location of electrical contacts results in a wide range of neuron behavior. Additionally, implementation of an asymmetric notch allows for nonlinear pinning which increased expressivity without sacrificing leaking. The measured behavior is implemented in a simulated spiking neural network that outperforms a 1D model of continuous DW motion and approaches the performance of an ideal LIF activation function. The results show that the analog LIF capability of DW-MTJ neurons combines many desirable neuron functions into a single device, which can result in varied forms of multifunctional neuromorphic computing.

42 ENGINEERING↗
NASA NTRS1995

Neural Network Burst Pressure Prediction in Graphite/Epoxy Pressure Vessels from Acoustic Emission Amplitude Data

Acoustic emission (AE) data were taken during hydroproof for three sets of ASTM standard 5.75 inch diameter filament wound graphite/epoxy bottles. All three sets of bottles had the same design and were wound from the same graphite fiber; the only difference was in the epoxies used. Two of the epoxies had similar mechanical properties, and because the acoustic properties of materials are a function of their stiffnesses, it was thought that the AE data from the two sets might also be similar; however, this was not the case. Therefore, the three resin types were categorized using dummy variables, which allowed the prediction of burst pressures all three sets of bottles using a single neural network. Three bottles from each set were used to train the network. The resin category, the AE amplitude distribution data taken up to 25 % of the expected burst pressure, and the actual burst pressures were used as inputs. Architecturally, the network consisted of a forty-three neuron input layer (a single categorical variable defining the resin type plus forty-two continuous variables for the AE amplitude frequencies), a fifteen neuron hidden layer for mapping, and a single output neuron for burst pressure prediction. The network trained on all three bottle sets was able to predict burst pressures in the remaining bottles with a worst case error of + 6.59%, slightly greater than the desired goal of + 5%. This larger than desired error was due to poor resolution in the amplitude data for the third bottle set. When the third set of bottles was eliminated from consideration, only four hidden layer neurons were necessary to generate a worst case prediction error of - 3.43%, well within the desired goal.

Hill, Eric v. K.↗
DOE OSTI2021

An artificial spiking quantum neuron

Abstract Artificial spiking neural networks have found applications in areas where the temporal nature of activation offers an advantage, such as time series prediction and signal processing. To improve their efficiency, spiking architectures often run on custom-designed neuromorphic hardware, but, despite their attractive properties, these implementations have been limited to digital systems. We describe an artificial quantum spiking neuron that relies on the dynamical evolution of two easy to implement Hamiltonians and subsequent local measurements. The architecture allows exploiting complex amplitudes and back-action from measurements to influence the input. This approach to learning protocols is advantageous in the case where the input and output of the system are both quantum states. We demonstrate this through the classification of Bell pairs which can be seen as a certification protocol. Stacking the introduced elementary building blocks into larger networks combines the spatiotemporal features of a spiking neural network with the non-local quantum correlations across the graph.

Kristensen, Lasse Bjørn (ORCID:0000000239398170)↗
DOE OSTI2024

Explaining Neural Spike Activity for Simulated Bio-plausible Network through Deep Sequence Learning

With significant improvements in large-scale simulations of brain models, there is a growing need to develop tools for rapid analysis and interpreting the simulation results. In this work, we explore the potential of sequential deep learning models to understand and explain the network dynamics among the neurons extracted from a large-scale neural simulation in STACS (Simulation Tool for Asynchronous Cortical Stream). Our method employs a representative neuroscience model that abstracts the cortical dynamics with a reservoir of randomly connected spiking neurons with a low stable spike firing rate throughout the simulation duration. We subsequently analyze the spike dynamics of the simulated spiking neural network through an autoencoder model and an attention-based mechanism.

Kulkarni, Shruti↗
NASA NTRS1990

Identification of the connections in biologically inspired neural networks

We developed an identification method to find the strength of the connections between neurons from their behavior in small biologically-inspired artificial neural networks. That is, given the network external inputs and the temporal firing pattern of the neurons, we can calculate a solution for the strengths of the connections between neurons and the initial neuron activations if a solution exists. The method determines directly if there is a solution to a particular neural network problem. No training of the network is required. It should be noted that this is a first pass at the solution of a difficult problem. The neuron and network models chosen are related to biology but do not contain all of its complexities, some of which we hope to add to the model in future work. A variety of new results have been obtained. First, the method has been tailored to produce connection weight matrix solutions for networks with important features of biological neural (bioneural) networks. Second, a computationally efficient method of finding a robust central solution has been developed. This later method also enables us to find the most consistent solution in the presence of noisy data. Prospects of applying our method to identify bioneural network connections are exciting because such connections are almost impossible to measure in the laboratory. Knowledge of such connections would facilitate an understanding of bioneural networks and would allow the construction of the electronic counterparts of bioneural networks on very large scale integrated (VLSI) circuits.

Demuth, H.↗
NASA NTRS1989

Monolithically integrated two-dimensional arrays of optoelectronic threshold devices for neural network applications

A monolithic 10 x 10 two-dimensional array of 'optical neuron' optoelectronic threshold elements for neural network applications has been designed, fabricated, and tested. Overall array dimensions are 5 x 5 mm, while the individual neurons, composed of an LED that is driven by a double-heterojunction bipolar transistor, are 250 x 250 microns. The overall integrated structure exhibited semiconductor-controlled rectifier characteristics, with a breakover voltage of 75 V and a reverse-breakdown voltage of 60 V; this is attributable to the parasitic p-n-p transistor which exists as a result of the sharing of the same n-AlGaAs collector between the transistors and the LED.

Kim, J. H.↗
NASA NTRS1995

Lyapunov exponents from CHUA's circuit time series using artificial neural networks

In this paper we present the general problem of identifying if a nonlinear dynamic system has a chaotic behavior. If the answer is positive the system will be sensitive to small perturbations in the initial conditions which will imply that there is a chaotic attractor in its state space. A particular problem would be that of identifying a chaotic oscillator. We present an example of three well known different chaotic oscillators where we have knowledge of the equations that govern the dynamical systems and from there we can obtain the corresponding time series. In a similar example we assume that we only know the time series and, finally, in another example we have to take measurements in the Chua's circuit to obtain sample points of the time series. With the knowledge about the time series the phase plane portraits are plotted and from them, by visual inspection, it is concluded whether or not the system is chaotic. This method has the problem of uncertainty and subjectivity and for that reason a different approach is needed. A quantitative approach is the computation of the Lyapunov exponents. We describe several methods for obtaining them and apply a little known method of artificial neural networks to the different examples mentioned above. We end the paper discussing the importance of the Lyapunov exponents in the interpretation of the dynamic behavior of biological neurons and biological neural networks.

Gonzalez, J. Jesus↗
DOE OSTI2022

Devices and methods for increasing the speed and efficiency at which a computer is capable of modeling a plurality of random walkers using a particle method

A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space. The method also includes either assigning a corresponding set of ringed neurons in a spiking neural network to a corresponding virtual random walker, or assigning a corresponding set of ringed neurons to a point in the virtual space. Movement of a given virtual random walker is tracked by decoding differences between states of individual neurons in a corresponding given set of ringed neurons. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network.

Aimone, James Bradley↗
DOE OSTI2025

The chromatin remodeler ADNP regulates neurodevelopmental disorder risk genes and neocortical neurogenesis

Although chromatin remodelers are among the most important risk genes associated with neurodevelopmental disorders (NDDs), the roles of these complexes during brain development are in many cases unclear. Here, we focused on the recently discovered ChAHP chromatin remodeling complex. The zinc finger and homeodomain transcription factor ADNP is a core subunit of this complex, and de novoADNPmutations lead to intellectual disability and autism spectrum disorder. However, germlineAdnpknockout mice were previously shown to exhibit early embryonic lethality, obscuring subsequent roles for the ChAHP complex in neurogenesis. To circumvent this early developmental arrest, we generated a conditionalAdnpmutant allele. Using single-cell transcriptomics, cut&run-seq, and histological approaches, we show that during neocortical development, Adnp orchestrates the production of late-born, upper-layer neurons through a two-step process. First, Adnp is required to sustain progenitor proliferation specifically during the developmental window for upper-layer cortical neurogenesis. Accordingly, we found that Adnp recruits the ChAHP subunit Chd4 to genes associated with progenitor proliferation. Second, in postmitotic differentiated neurons, we define a network of risk genes linked to NDDs that are regulated by Adnp and Chd4. Taken together, these data demonstrate that ChAHP is critical for driving the expansion of upper-layer cortical neurons and for regulating neuronal gene expression programs, suggesting that these processes may potentially contribute to NDD etiology.

Science & Technology - Other Topics↗
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 OSTI2022

Deep Neural Network Algorithm for CMC Microstructure Characterization and Variability Quantification

Microstructure characterization and variability quantification are crucial for understanding ceramic matrix composites (CMCs) mechanical behavior and deformation mechanisms across length scales. Traditionally, analyses of the micrographs obtained from microscopy are labor-intensive. However, with the vast improvement in computer vision (CV) and deep learning (DL), an automated algorithm can be designed to extract essential microstructure variability from micrographs which can then be used to construct a statistically representative volume element (SRVE). The DL-based algorithm spans the taxonomy of microstructure analyses, including semantic segmentation of microstructure constituents, secondary phases, matrix/fiber interface, and defects, and quantifying the microstructure variability in terms of probability distributions. In this work, C/SiNC and SiC/SiNC CMCs microstructures are semantically segmented through a deep convolutional neural network, followed by variability quantification through the implementation of a fully connected regression layer, hence forming a deep regression network. The deep regression network operates in a feedforward regime, in which the neuron output signal traverses through the network in a unidirectional manner. The weight tensor associated with each layer is updated through a backpropagation stochastic gradient descent approach. The input gray-scale image obtained through in-house scanning electron microscope and confocal microscope micrographs is augmented through affine transformations to increase the training set size, which is then processed through four strided convolutional layers. This compresses the image resolution by half at each layer while increasing the image depth by applying different filters (image encoding). The class activation maps (CAMs) corresponding to the applied filters highlight the key architectural features and assist with the semantic segmentation of the microstructure.

Hamza, Mohamed H.↗