Search NASA⌕ Search

SEARCH · Search NASA

Results for “neural function”

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
NASA NTRS1993

Radial basis function network learns ceramic processing and predicts related strength and density

Radial basis function (RBF) neural networks were trained using the data from 273 Si3N4 modulus of rupture (MOR) bars which were tested at room temperature and 135 MOR bars which were tested at 1370 C. Milling time, sintering time, and sintering gas pressure were the processing parameters used as the input features. Flexural strength and density were the outputs by which the RBF networks were assessed. The 'nodes-at-data-points' method was used to set the hidden layer centers and output layer training used the gradient descent method. The RBF network predicted strength with an average error of less than 12 percent and density with an average error of less than 2 percent. Further, the RBF network demonstrated a potential for optimizing and accelerating the development and processing of ceramic materials.

Cios, Krzysztof J.↗
NASA NTRS2013

Prediction of Visual Acuity from Wavefront Aberrations

A method for generating a visual acuity metric, based on wavefront aberrations (WFAs), associated with a test subject and representing classes of imperfections, such as defocus, astigmatism, coma and spherical aberrations, of the subject's visual system. The metric allows choices of different image template, can predict acuity for different target probabilities, can incorporate different and possibly subject-specific neural transfer functions, can predict acuity for different subject templates, and incorporates a model of the optotype identification task.

Watson, Andrew B.↗
NASA NTRSDate not supplied

Normative Baseline Oculomotor Performance

Future missions to the moon or Mars will require the crew to monitor and assess their health and performance more autonomously, necessitating approaches that are easily useable and interpretable by non-clinicians. The eye-movement-based performance metrics (oculometrics) obtained from NASA-patented technology developed at the Visuomotor Control Laboratory can reliably detect and discriminate the source of mild neural impairment relative to an individual’s baseline visual and sensorimotor performance and can predict performance in manual control tasks. This study aims to develop a database of normative performance that can be used to enable the detection of impairment without a within-subject baseline and to facilitate power analyses for the design of future studies.

eye movements↗
NASA NTRSDate not supplied

Oxidative Stress and Neuroconsequences of the Spaceflight Environment –A 5-ion GCRsim Dose-response Study

The overall scope of this project is to test the hypothesis that Ionizing Radiation (IR), microgravity and social isolation combine synergistically to trigger an oxidative stress response that alters immune homeostasis, brain structure/function, and neurobehavioral/cognitive performance. Specific Aims for this project are to: (1) Determine dose-response curves for acute ‘Five-Ion GCR Simulation’ exposure for immune, brain and performance responses in crew age-matched adult male and female mice; (2) Determine effects of acute ‘Five-Ion GCR Simulation’ exposure singly and in combination with simulated microgravity and social isolation, on immune, brain and performance responses in crew age-matched male and female mice mimicking deep space missions; and (3) Determine efficacy of the dietary antioxidant, Nicotinamide Mononucleotide (NMN), a key intermediate in nicotinamide adenine dinucleotide (NAD+) biosynthesis. Here we exposed mature (23-24-week-old) male and female mice to simulated 5-Ion GCR (either 0, 5, 15, or 50cGy) at the NASA Space Radiation Laboratory (NSRL). Across ‘Acute’ (IR+72hrs and IR+14 days) and ‘Delayed’ (IR+28 to IR+124 days) phases of the 6-month-long study, we assessed immune, neural, and functional (sensorimotor/behavioral/cognitive) responses anticipated during a transit to Mars. This presentation will report on dose-response curves for 5-ion GCRsim related to potential biomarkers; structural/functional changes in the immune and nervous systems; and behavioral/cognitive performance deficits. This project addresses NASA’s efforts to characterize risks and identify appropriate countermeasures in anticipation of future deep space missions. Ensuring crew health and performance during extended transits necessitates that sensorimotor and cognitive abilities remain strong to avoid potentially catastrophic health and safety outcomes.

deep space↗
NASA NTRS2021

Predicting the Functional State of Protein Kinases Using Interpretable Graph Neural Networks

Kinases are a family of proteins that function as molecular switches, regulating several essential cellular activities such as cell proliferation. Dysfunctional kinases are implicated in several types of cancers and hence they are actively pursued as drug targets. Given the vast number of complex kinase structures that are available in the protein data bank (PDB), there is a necessity to develop methodologies that can identify structurally important moieties of the kinases in an automated fashion, for such techniques can be instrumental in identifying novel drug targets. In this work, we develop a graph neural network (GNN) based deep learning framework for classifying the functionally active and inactive states of a large set of eukaryotic protein kinases, making use of their 3D structure from the PDB. We show that GNN based machine learning models can classify protein states with an accuracy greater than 97%. We further use the GNN models to automatically identify regions of the kinases that are important for its function. For this purpose, Gradient-weighted Class Activation Mapping (Grad-CAM) was implemented on the protein graphs. Remarkably, Grad-CAM consistently identifies the highly conserved DFG motif as the most important part of the protein across the entire kinome, without any prior input. Other regions of the hydrophobic core such as the HRD motif were also identified by the interpretable GNN framework, consistent with the literature. We discuss the significance of each of these regions in detail.

Ashwin Ravichandran↗
DOE OSTI2025

Improved loss functions for machine-learned atomic potentials

Machine learning (ML) has become an invaluable tool across a wide array of domains in science as researchers find new ways to leverage its predictive power. This is especially true in chemistry, where ML is used to fit chemical properties or desirable attributes to the local structure of molecules and materials. In the pursuit of greater accuracy, it is relatively simple to increase the size or complexity of such models, although this often requires simultaneously seeking larger datasets in order to both fit and interpret the larger number of parameters. However, it is equally important to assess the quality and relative importance of the data and how these factors impact the training process. We, therefore, investigate the impact of using different loss functions for training neural network potentials (NNPs), as the loss function defines the error and parameter gradients used to train the NNP. In particular, we test the mean-squared error and Huber loss functions and, using insight from these functions, derive a new loss function based on the Asinh function, which yields significant improvement in the accuracy and generality of NNPs. We show that by discounting/minimizing errors and anomalies in the optimization process, both the Huber and Asinh loss functions improve the training of NNPs, leading to a final potential with a greater effective dimensionality.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1994

Automated Induction Of Rule-Based Neural Networks

Prototype expert systems implemented in software and are functionally equivalent to neural networks set up automatically and placed into operation within minutes following information-theoretic approach to automated acquisition of knowledge from large example data bases. Approach based largely on use of ITRULE computer program.

Smyth, Padhraic J.↗
DOE OSTI2025

Uncertainty propagation in feed-forward neural network models

We develop new uncertainty propagation methods for feed-forward neural network architectures with leaky ReLU activation functions subject to random perturbations in the input vectors. In particular, we derive analytical expressions for the probability density function (PDF) of the neural network output and its statistical moments as a function of the input uncertainty and the parameters of the network, i.e., weights and biases. A key finding is that an appropriate linearization of the leaky ReLU activation function yields accurate statistical results even for large perturbations in the input vectors. This can be attributed to the way information propagates through the network. We also propose new analytically tractable Gaussian copula surrogate models to approximate the full joint PDF of the neural network output. To validate our theoretical results, we conduct Monte Carlo simulations and a thorough error analysis on a multi-layer neural network representing a nonlinear integro-differential operator between two polynomial function spaces. Our findings demonstrate excellent agreement between the theoretical predictions and Monte Carlo simulations.

MLP networks↗
NASA NTRS2003

The expression and function of the achaete-scute genes in Tribolium castaneum reveals conservation and variation in neural pattern formation and cell fate specification

The study of achaete-scute (ac/sc) genes has recently become a paradigm to understand the evolution and development of the arthropod nervous system. We describe the identification and characterization of the ac/sc genes in the coleopteran insect species Tribolium castaneum. We have identified two Tribolium ac/sc genes - achaete-scute homolog (Tc-ASH) a proneural gene and asense (Tc-ase) a neural precursor gene that reside in a gene complex. Focusing on the embryonic central nervous system we find that Tc-ASH is expressed in all neural precursors and the proneural clusters from which they segregate. Through RNAi and misexpression studies we show that Tc-ASH is necessary for neural precursor formation in Tribolium and sufficient for neural precursor formation in Drosophila. Comparison of the function of the Drosophila and Tribolium proneural ac/sc genes suggests that in the Drosophila lineage these genes have maintained their ancestral function in neural precursor formation and have acquired a new role in the fate specification of individual neural precursors. Furthermore, we find that Tc-ase is expressed in all neural precursors suggesting an important and conserved role for asense genes in insect nervous system development. Our analysis of the Tribolium ac/sc genes indicates significant plasticity in gene number, expression and function, and implicates these modifications in the evolution of arthropod neural development.

Non-NASA Center↗
NASA NTRS2003

The Expression and Function of the Achaete-Scute Genes in Tribolium castaneum Reveals Conservation and Variation in Neural Pattern Formation and Cell Fate Specification

SUMMARY The study of achaete-scute (ac/sc) genes has recently become a paradigm to understand the evolution and development of the arthropod nervous system. We describe the identification and characterization of the ache genes in the coleopteran insect species Tribolium castaneum. We have identified two Tribolium ache genes - achaete-scute homolog (Tc-ASH) a proneural gene and asense (Tc-ase) a neural precursor gene that reside in a gene complex. Focusing on the embryonic central nervous system we fmd that Tc-ASH is expressed in all neural precursors and the proneural clusters from which they segregate. Through RNAi and misexpression studies we show that Tc-ASH is necessary for neural precursor formation in Triboliurn and sufficient for neural precursor formation in Drosophila. Comparison of the function of the Drosophila and Triboliurn proneural ac/sc genes suggests that in the Drosophila lineage these genes have maintained their ancestral function in neural precursor formation and have acquired a new role in the fate specification of individual neural precursors. Furthermore, we find that Tc-use is expressed in all neural precursors suggesting an important and conserved role for asense genes in insect nervous system development. Our analysis of the Triboliurn ache genes indicates significant plasticity in gene number, expression and function, and implicates these modifications in the evolution of arthropod neural development.

Wheeler, Scott R.↗
NASA NTRS1992

Using neural networks and Dyna algorithm for integrated planning, reacting and learning in systems

The traditional AI answer to the decision making problem for a robot is planning. However, planning is usually CPU-time consuming, depending on the availability and accuracy of a world model. The Dyna system generally described in earlier work, uses trial and error to learn a world model which is simultaneously used to plan reactions resulting in optimal action sequences. It is an attempt to integrate planning, reactive, and learning systems. The architecture of Dyna is presented. The different blocks are described. There are three main components of the system. The first is the world model used by the robot for internal world representation. The input of the world model is the current state and the action taken in the current state. The output is the corresponding reward and resulting state. The second module in the system is the policy. The policy observes the current state and outputs the action to be executed by the robot. At the beginning of program execution, the policy is stochastic and through learning progressively becomes deterministic. The policy decides upon an action according to the output of an evaluation function, which is the third module of the system. The evaluation function takes the following as input: the current state of the system, the action taken in that state, the resulting state, and a reward generated by the world which is proportional to the current distance from the goal state. Originally, the work proposed was as follows: (1) to implement a simple 2-D world where a 'robot' is navigating around obstacles, to learn the path to a goal, by using lookup tables; (2) to substitute the world model and Q estimate function Q by neural networks; and (3) to apply the algorithm to a more complex world where the use of a neural network would be fully justified. In this paper, the system design and achieved results will be described. First we implement the world model with a neural network and leave Q implemented as a look up table. Next, we use a lookup table for the world model and implement the Q function with a neural net. Time limitations prevented the combination of these two approaches. The final section discusses the results and gives clues for future work.

Lima, Pedro↗
NASA NTRS1993

Geometrical approach to neural net control of movements and posture

In one approach to modeling brain function, sensorimotor integration is described as geometrical mapping among coordinates of non-orthogonal frames that are intrinsic to the system; in such a case sensors represent (covariant) afferents and motor effectors represent (contravariant) motor efferents. The neuronal networks that perform such a function are viewed as general tensor transformations among different expressions and metric tensors determining the geometry of neural functional spaces. Although the non-orthogonality of a coordinate system does not impose a specific geometry on the space, this "Tensor Network Theory of brain function" allows for the possibility that the geometry is non-Euclidean. It is suggested that investigation of the non-Euclidean nature of the geometry is the key to understanding brain function and to interpreting neuronal network function. This paper outlines three contemporary applications of such a theoretical modeling approach. The first is the analysis and interpretation of multi-electrode recordings. The internal geometries of neural networks controlling external behavior of the skeletomuscle system is experimentally determinable using such multi-unit recordings. The second application of this geometrical approach to brain theory is modeling the control of posture and movement. A preliminary simulation study has been conducted with the aim of understanding the control of balance in a standing human. The model appears to unify postural control strategies that have previously been considered to be independent of each other. Third, this paper emphasizes the importance of the geometrical approach for the design and fabrication of neurocomputers that could be used in functional neuromuscular stimulation (FNS) for replacing lost motor control.

Review↗
DOE OSTI2024

Polyconvex neural network models of thermoelasticity

Machine-learning function representations such as neural networks have proven to be excellent constructs for constitutive modeling due to their flexibility to represent highly nonlinear data and their ability to incorporate constitutive constraints, which also allows them to generalize well to unseen data. Here, in this work, we extend a polyconvex hyperelastic neural network framework to (isotropic) thermo-hyperelasticity by specifying the thermodynamic and material theoretic requirements for an expansion of the Helmholtz free energy expressed in terms of deformation invariants and temperature. Different formulations which a priori ensure polyconvexity with respect to deformation and concavity with respect to temperature are proposed and discussed. The physics-augmented neural networks are furthermore calibrated with a recently proposed sparsification algorithm that not only aims to fit the training data but also penalizes the number of active parameters, which prevents overfitting in the low data regime and promotes generalization. The performance of the proposed framework is demonstrated on synthetic data, which illustrate the expected thermomechanical phenomena, and existing temperature-dependent uniaxial tension and tension-torsion experimental datasets.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Adaptive Interface-PINNs (AdaI-PINNs) for inverse problems: Determining material properties for heterogeneous systems

Here, we determine spatially varying discontinuous material properties using a domain-decomposition based physics-informed neural networks (PINNs) framework named the Adaptive Interface-PINNs or AdaI-PINNs (Roy et al., 2024). We propose the use of distinct neural networks for the field variables and material properties within each material, utilizing adaptive activation functions. While the neural networks across different materials share the same weights and biases, their activation functions are uniquely tailored using a hyperparameter that influences the slope of the activation function. The proposed framework is tested on several one-dimensional and two-dimensional benchmark examples, and its performance is compared with conventional PINNs and existing domain-decomposition PINNs frameworks, namely, the Multi-domain physics-informed neural network (M-PINN), and the eXtended physics-informed neural networks (XPINNs). The results demonstrate that the proposed approach can determine randomly distributed discontinuous material properties with an L 2 error of $\mathscr{O}$ (10 -3 ) for the material property and the root-mean-square error of $\mathscr{O}$ (10 -3 ) for the primary variable while the other approaches yield errors that are approximately two orders of magnitude larger (that is, $\mathscr{O}$ (10 -1 )). Moreover, the spatial distribution of material properties obtained using the proposed framework is in close agreement with the true distribution, whereas the other approaches fare much worse. Additionally, the proposed approach is approximately 40% faster than its competitors, indicating its potential as a robust alternative for solving inverse problems in heterogeneous materials.

36 MATERIALS SCIENCE↗
DOE OSTI2025

A resolution independent neural operator

The Deep operator network (DeepONet) is a powerful yet simple neural operator architecture that utilizes two deep neural networks to learn mappings between infinite-dimensional function spaces. This architecture is highly flexible, allowing the evaluation of the solution field at any location within the desired domain. However, it imposes a strict constraint on the input space, requiring all input functions to be discretized at the same locations; this limits its practical applications. Here, in this work, we introduce a general framework for operator learning from input–output data with arbitrary number and locations of sensors. This begins by introducing a resolution-independent DeepONet (RI-DeepONet), enabling it to handle input functions that are arbitrarily, but sufficiently finely, discretized. To this end, we propose two dictionary learning algorithms to adaptively learn a set of appropriate continuous basis functions, parameterized as implicit neural representations (INRs), from correlated signals defined on arbitrary point cloud data. These basis functions are then used to project arbitrary input function data as a point cloud onto an embedding space (i.e., a vector space of finite dimensions) with dimensionality equal to the dictionary size, which can be directly used by DeepONet without any architectural changes. In particular, we utilize sinusoidal representation networks (SIRENs) as trainable INR basis functions. The introduced dictionary learning algorithms are then used in a similar way to learn an appropriate dictionary of basis functions for the output function data, which defines a new neural operator architecture referred to as the R esolution I ndependent N eural O perator (RINO). In the RINO, the operator learning task simplifies to learning a mapping from the coefficients of input basis functions to the coefficients of output basis functions. We demonstrate the robustness and applicability of RINO in handling arbitrarily (but sufficiently richly) sampled input and output functions during both training and inference through several numerical examples.

Deep operator network (DeepONet)↗
DOE OSTI2026

Lyapunov-Based Iterative Learning of the Region of Attraction for Autonomous Systems

This presentation introduces a novel algorithm for estimating the region of attraction of equilibrium points for nonlinear discrete-time autonomous systems. The method iteratively expands an initial estimate of the region of attraction by constructing unions of sublevel sets of learned functions parametrized as neural networks. Unlike conventional techniques that rely on a single global Lyapunov function, the proposed approach provides a collection of local Lyapunov-like functions, enabling richer representations and potentially larger region of attraction estimates. These functions are trained using sampled state-space data, and their Lipschitz continuity ensures that desirable properties extend beyond the training samples. The devised strategy is tested via numerical simulations, demonstrating the effectiveness of the proposed approach.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2015

A Wirelessly Powered Micro-Spectrometer for Neural Probe-Pin Device

Treatment of neurological anomalies, places stringent demands on device functionality and size. A micro-spectrometer has been developed for use as an implantable neural probe to monitor neuro-chemistry in synapses. The microspectrometer, based on a NASA-invented miniature Fresnel grating, is capable of differentiating the emission spectra from various brain tissues. The micro-spectrometer meets the size requirements, and is able to probe the neuro-chemistry and suppression voltage typically associated with a neural anomaly. This neural probe-pin device (PPD) is equipped with wireless power technology (WPT) enabling operation in a continuous manner without requiring an implanted battery. The implanted neural PPD, together with a neural electronics interface and WPT, allow real-time measurement and control/feedback for remediation of neural anomalies. The design and performance of the combined PPD/WPT device for monitoring dopamine in a rat brain will be presented to demonstrate the current level of development. Future work on this device will involve the addition of an embedded expert system capable of performing semi-autonomous management of neural functions through a routine of sensing, processing, and control.

Choi, Sang H.↗