Search NASA⌕ Search

SEARCH · Search NASA

Results for “network inference”

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 217 records · Page 12

Coupling Genome-wide Transcriptomics and Developmental Toxicity Profiles in Zebrafish to Characterize Polycyclic Aromatic Hydrocarbon (PAH) Hazard

Polycyclic Aromatic Hydrocarbons (PAHs) are diverse environmental pollutants associated with adverse human health effects. Many studies focus on the carcinogenic effects of a limited number of PAHs and there is an increasing need to understand mechanisms of developmental toxicity of more varied yet environmentally relevant PAHs. A previous study characterized the developmental toxicity of 123 PAHs in zebrafish. Based on phenotypic responses ranging from complete inactivity to acute mortality, we classified these PAHs into eight bins, selected 16 representative PAHs, and exposed developing zebrafish to the concentration of each PAH that induced 80% phenotypic effect. We conducted RNA sequencing at 48 h post fertilization to identify gene expression changes as a result of PAH exposure. Using the Context Likelihood of Relatedness algorithm, we inferred a network that links the PAHs based on coordinated gene responses to PAH exposure. The 16 PAHs formed two broad clusters: Cluster A was transcriptionally more similar to the controls, while Cluster B consisted of PAHs that were generally more developmentally toxic, significantly elevated cyp1a transcript levels, and induced Ahr2-dependent Cyp1a protein expression in the skin confirmed by gene-silencing studies. We found that cyp1a transcript levels were associated with transcriptomic response, but not with PAH developmental toxicity. While all cluster B PAHs predominantly activated Ahr2, they also each enriched unique pathways like ion transport signaling, which likely points to differing molecular events between the PAHs downstream of Ahr2. Thus, using a systems biology approach, we have begun to evaluate, classify, and define mechanisms of PAH toxicity.

59 BASIC BIOLOGICAL SCIENCES↗

Machine Learning 5G Attack Detection in Programmable Logic

Machine learning-assisted network security may significantly contribute to securing 5G components. However, machine learning network security inference speeds generally require tens to hundreds of milliseconds thereby introducing significant latency in 5G operations. The inference latency can be reduced by deploying the machine learning model to programmable logic in a field programmable gate array (FPGA) at the cost of a small loss in accuracy. In order to quantify this loss, as well as to establish baseline performance inference speeds for programmable logic implementations, this work explores an autoencoder and a ß-variational autoencoder deployed on two different FPGA evaluation boards and compares accuracy and performance against an NVIDIA A100 GPU implementation. A publicly available 5G dataset containing 10 types of attacks along with normal traffic is introduced as part of the evaluation.

97 MATHEMATICS AND COMPUTING↗

Risk-Informed Condition Evaluation of Solar-centered Energy Generation and Distribution Networks through Bayesian Learning and Inference

We develop a methodology based on Bayesian inference over Probabilistic Graphical Models (PGMs) to understand and quantify risk in solar-centered grids using targeted measurements and learned system behavior. Being non-prescriptive but, rather, able to infer system behavior and, ultimately, address risk queries from data, our machine learning-type paradigm is tailored for diverse topologies and threat scenarios often associated with distributed energy generation and photovoltaic distributed energy resources (PV-DERs) in particular. We describe algorithmic processes for: (i) learning the structure of PGMs that result from attack-prone PV-DER-proliferated distribution systems, (ii) quantifying cause-effect relationships, and (iii) evaluating risk queries based on diverse evidence. The contributions are illustrated on a residential grid subject to output impairment attacks on its PV-DER infrastructure.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Flow over an espresso cup: inferring 3-D velocity and pressure fields from tomographic background oriented Schlieren via physics-informed neural networks

Tomographic background oriented Schlieren (Tomo-BOS) imaging measures density or temperature fields in three dimensions using multiple camera BOS projections, and is particularly useful for instantaneous flow visualizations of complex fluid dynamics problems. We propose a new method based on physics-informed neural networks (PINNs) to infer the full continuous three-dimensional (3-D) velocity and pressure fields from snapshots of 3-D temperature fields obtained by Tomo-BOS imaging. The PINNs seamlessly integrate the underlying physics of the observed fluid flow and the visualization data, hence enabling the inference of latent quantities using limited experimental data. In this hidden fluid mechanics paradigm, we train the neural network by minimizing a loss function composed of a data mismatch term and residual terms associated with the coupled Navier–Stokes and heat transfer equations. We first quantify the accuracy of the proposed method based on a two-dimensional synthetic data set for buoyancy-driven flow, and subsequently apply it to the Tomo-BOS data set, where we are able to infer the instantaneous velocity and pressure fields of the flow over an espresso cup based only on the temperature field provided by the Tomo-BOS imaging. Moreover, we conduct an independent PIV experiment to validate the PINN inference for the unsteady velocity field at a centre plane. To explain the observed flow physics, we also perform systematic PINN simulations at different Reynolds and Richardson numbers and quantify the variations in velocity and pressure fields. Furthermore, the results in this paper indicate that the proposed deep learning technique can become a promising direction in experimental fluid mechanics.

97 MATHEMATICS AND COMPUTING↗

CrossSim Inference Manual v2.0

Neural networks are largely based on matrix computations. During forward inference, the most heavily used compute kernel is the matrix-vector multiplication (MVM): $W \vec{x} $. Inference is a first frontier for the deployment of next-generation hardware for neural network applications, as it is more readily deployed in edge devices, such as mobile devices or embedded processors with size, weight, and power constraints. Inference is also easier to implement in analog systems than training, which has more stringent device requirements. The main processing kernel used during inference is the MVM.

97 MATHEMATICS AND COMPUTING↗

Systematic network assessment of the carcinogenic activities of cadmium

Cadmium has been defined as type I carcinogen for humans, but the underlying mechanisms of its carcinogenic activity and its influence on protein-protein interactions in cells are not fully elucidated. The aim of the current study was to evaluate, systematically, the carcinogenic activity of cadmium with systems biology approaches. From a literature search of 209 studies that performed with cellular models, 208 proteins influenced by cadmium exposure were identified. All of these were assessed by Western blotting and were recognized as key nodes in network analyses. The protein-protein functional interaction networks were constructed with NetBox software and visualized with Cytoscape software. These cadmium-rewired genes were used to construct a scale-free, highly connected biological protein interaction network with 850 nodes and 8770 edges. Of the network, nine key modules were identified and 60 key signaling pathways, including the estrogen, RAS, PI3K-Akt, NF-κB, HIF-1α, Jak-STAT, and TGF-β signaling pathways, were significantly enriched. With breast cancer, colorectal and prostate cancer cellular models, we validated the key node genes in the network that had been previously reported or inferred form the network by Western blotting methods, including STAT3, JNK, p38, SMAD2/3, P65, AKT1, and HIF-1α. These results suggested the established network was robust and provided a systematic view of the carcinogenic activities of cadmium in human. - Highlights: • A cadmium-influenced network with 850 nodes and 8770 edges was established. • The cadmium-rewired gene network was scale-free and highly connected. • Nine modules were identified, and 60 key signaling pathways related to cadmium-induced carcinogenesis were found. • Key mediators in the network were validated in multiple cellular models.

60 APPLIED LIFE SCIENCES↗

O3BNN-R: An Out-Of-Order Architecture for High-Performance and Regularized BNN Inference

Binarized Neural Networks (BNN) have drawn tremendous attention due to significantly reduced computational complexity and memory demand. They have especially shown great potential in cost- and power-restricted domains, such as IoT and smart edge-devices, where reaching a certain accuracy bar is often sufficient, and real-time is highly desired.In this work, we demonstrate that the highly-condensed BNN model can be shrunk significantly further by dynamically pruning irregular redundant edges. Based on two new observations on BNN-specific properties, an out-of-order (OoO) architecture – O3BNN-R, can curtail edge evaluation in cases where the binary output of a neuron can be determined early. Similar to Instruction-Level-Parallelism(ILP), these fine-grained, irregular, runtime pruning opportunities are traditionally presumed to be difficult to exploit. In order to increase the pruning opportunities, we also optimize the training process by adding 2 regularization items in the loss function (1) for pooling pruning and (2) for threshold pruning. We evaluate our design on an FPGA platform using three well-known networks, including VggNet-16, AlexNet for ImageNet, and a VGG-like network for Cifar-10.

Geng, Tong↗

Tailor : Altering Skip Connections for Resource-Efficient Inference

Deep neural networks use skip connections to improve training convergence. However, these skip connections are costly in hardware, requiring extra buffers and increasing on- and off-chip memory utilization and bandwidth requirements. In this article, we show that skip connections can be optimized for hardware when tackled with a hardware-software codesign approach. We argue that while a network’s skip connections are needed for the network to learn, they can later be removed or shortened to provide a more hardware-efficient implementation with minimal to no accuracy loss. We introduceTailor, a codesign tool whose hardware-aware training algorithm gradually removes or shortens a fully trained network’s skip connections to lower the hardware cost.Tailorimproves resource utilization by up to 34% for block random access memories (BRAMs), 13% for flip-flops (FFs), and 16% for look-up tables (LUTs) for on-chip, dataflow-style architectures.Tailorincreases performance by 30% and reduces memory bandwidth by 45% for a two-dimensional processing element array architecture.

Computer Science↗

Accelerating cosmological inference with Gaussian processes and neural networks – an application to LSST Y1 weak lensing and galaxy clustering

ABSTRACT Studying the impact of systematic effects, optimizing survey strategies, assessing tensions between different probes and exploring synergies of different data sets require a large number of simulated likelihood analyses, each of which cost thousands of CPU hours. In this paper, we present a method to accelerate cosmological inference using emulators based on Gaussian process regression and neural networks. We iteratively acquire training samples in regions of high posterior probability which enables accurate emulation of data vectors even in high dimensional parameter spaces. We showcase the performance of our emulator with a simulated 3×2 point analysis of LSST-Y1 with realistic theoretical and systematics modelling. We show that our emulator leads to high-fidelity posterior contours, with an order of magnitude speed-up. Most importantly, the trained emulator can be re-used for extremely fast impact and optimization studies. We demonstrate this feature by studying baryonic physics effects in LSST-Y1 3×2 point analyses where each one of our MCMC runs takes approximately 5 min. This technique enables future cosmological analyses to map out the science return as a function of analysis choices and survey strategy.

Astronomy & Astrophysics↗

Parameter inference with deep jointly informed neural networks

Abstract A common challenge in modeling inertial confinement fusion (ICF) experiments with computer simulations is that many of the simulation inputs are unknown and cannot be directly measured. Often, parameters that are measured in the experiment are used to infer the unknown inputs by solving the inverse problem: finding the set of simulation inputs that result in outputs consistent with the experimental observations. In ICF, this process is often referred to as a “post‐shot analysis.” Post‐shot analyses are challenging as the inverse problem is often highly degenerate, the input parameter space is vast, and simulations are computationally expensive. In this work, deep neural network models equipped with model uncertainty estimates are used to train inverse models, which map directly from output to input space, to find the distribution of post‐shot simulations that are consistent with experimental observations. The inverse model approach is compared to Markov chain Monte Carlo (MCMC) sampling of the forward model, which maps from input to output space, for parameter inference tasks of varying complexity. The inverse models perform best when searching vast parameter spaces for post‐shot simulations that are consistent with a large number of observables, where MCMC sampling can be prohibitively expensive. We demonstrate how augmenting inverse models with autoencoders enable the inclusion of several dozen observables in the inverse mapping, reducing the degeneracy of the model and improving the accuracy of the post‐shot analysis.

Humbird, Kelli D.↗

Truth-Valued-Flow Inference (TVFI) and its applications in approximate reasoning

The framework of the theory of Truth-valued-flow Inference (TVFI) is introduced. Even though there are dozens of papers presented on fuzzy reasoning, we think it is still needed to explore a rather unified fuzzy reasoning theory which has the following two features: (1) it is simplified enough to be executed feasibly and easily; and (2) it is well structural and well consistent enough that it can be built into a strict mathematical theory and is consistent with the theory proposed by L.A. Zadeh. TVFI is one of the fuzzy reasoning theories that satisfies the above two features. It presents inference by the form of networks, and naturally views inference as a process of truth values flowing among propositions.

Wang, Pei-Zhuang↗

Fuzzy/Neural Software Estimates Costs of Rocket-Engine Tests

The Highly Accurate Cost Estimating Model (HACEM) is a software system for estimating the costs of testing rocket engines and components at Stennis Space Center. HACEM is built on a foundation of adaptive-network-based fuzzy inference systems (ANFIS) a hybrid software concept that combines the adaptive capabilities of neural networks with the ease of development and additional benefits of fuzzy-logic-based systems. In ANFIS, fuzzy inference systems are trained by use of neural networks. HACEM includes selectable subsystems that utilize various numbers and types of inputs, various numbers of fuzzy membership functions, and various input-preprocessing techniques. The inputs to HACEM are parameters of specific tests or series of tests. These parameters include test type (component or engine test), number and duration of tests, and thrust level(s) (in the case of engine tests). The ANFIS in HACEM are trained by use of sets of these parameters, along with costs of past tests. Thereafter, the user feeds HACEM a simple input text file that contains the parameters of a planned test or series of tests, the user selects the desired HACEM subsystem, and the subsystem processes the parameters into an estimate of cost(s).

Douglas, Freddie↗

Rapid Inverse Parameter Inference Using Physics-Informed Neural Network

As Li-ion batteries become more essential in today's economy, tools need to be developed to accurately and rapidly diagnose a battery's internal state-of-health. Using a Li-ion battery's (high-rate) voltage response, it is proposed to determine a battery's internal state through Bayesian calibration. However, Bayesian calibration is notoriously slow and requires thousands of model runs. To accelerate parameter inference using Bayesian calibration, a surrogate model is developed to replace the underlying physics-based Li-ion model. Developing a surrogate model for rapid Bayesian calibration analysis is discussed for both the single particle model (SPM) and the pseudo two-dimensional (P2D) model. Surrogate models are constructed using physics-informed neural networks (PINNs) that encode the influence of internal properties on observed voltage responses. In practice, a neural network can be trained by: 1) using simulation results of the physics-based model (i.e., a data-loss approach); 2) using the residuals of the governing equations themselves (i.e., a physics-loss approach); or 3) using a combination of simulation results and governing equation residuals. In the present work, PINNs are developed using a variety of training losses and neural network architectures. In this analysis, it is shown that a PINN surrogate model can be reliably trained with only physics-informed loss. However, using a coupled data-informed and physics-loss approach produced the most accurate PINNs.

Bayesian calibration↗

Efficient Neural Network Approaches for Conditional Optimal Transport with Applications in Bayesian Inference

In this work, we present two neural network approaches that approximate the solutions of static and dynamic conditional optimal transport (COT) problems. Both approaches enable conditional sampling and conditional density estimation, which are core tasks in Bayesian inference—particularly in the simulation-based (“likelihood-free”) setting. Our methods represent the target conditional distribution as a transformation of a tractable reference distribution. Obtaining such a transformation, chosen here to be an approximation of the COT map, is computationally challenging even in moderate dimensions. To improve scalability, our numerical algorithms use neural networks to parameterize candidate maps and further exploit the structure of the COT problem. Our static approach approximates the map as the gradient of a partially input convex neural network. It uses a novel numerical implementation to increase computational efficiency compared to state-of-the-art alternatives. Our dynamic approach approximates the conditional optimal transport via the flow map of a regularized neural ODE; compared to the static approach, it is slower to train but offers more modeling choices and can lead to faster sampling. We demonstrate both algorithms numerically, comparing them with competing state-of-the-art approaches, using benchmark datasets and simulation-based Bayesian inverse problems.

97 MATHEMATICS AND COMPUTING↗

Filtering in Hybrid Dynamic Bayesian Networks

We demonstrate experimentally that inference in a complex hybrid Dynamic Bayesian Network (DBN) is possible using the 2 - T i e Slice DBN (2T-DBN) from [Koller & Lerner, 20001 to model fault detection in a watertank system. In [Koller & Lerner, 20001 a generic Particle Filter (PF) is used for inference. We extend the experiment and perform approximate inference using The Extended Kalman Filter (EKF) and the Unscented Kalman Filter (UKF). Furthermore, we combine these techniques in a 'non-strict' Rao-Blackwellisation framework and apply it to the watertank system. We show that UKF and UKF in a PF framework outperfom the generic PF, EKF and EKF in a PF framework with respect to accuracy and robustness in terms of estimation RMSE. Especially we demonstrate the superiority of UKF in a PF framework when our beliefs of how data was generated are wrong. We also show that the choice of network structure is very important for the performance of the generic PF and the EKF algorithms, but not for the UKF algorithms. Furthermore, we investigate the influence of data noise in the water[ank simulation. Theory and implementation is based on the theory presented.

Andersen, Morten Nonboe↗

Peak Prediction Using Multi Layer Perceptron (MLP) for Edge Computing ASICs Targeting Scientific Applications

High data rate detectors play an integral part in scientific research and their development is actively pursued at High Energy Physics (HEP) facilities around the world. Edge Machine Learning (ML) offers the ability to reduce data rates by integrating ML algorithms into Application Specific Integrated Circuits (ASICs) on the front end electronics. In this work, we explore a set of neural network architectures for predicting the peak amplitudes in the detector's sensor response. We have designed and synthesized several MLP based neural networks comparing their inference accuracy, power consumption, and area targeting for minimal latency. The neural networks are synthesized in a commercial 65nm process. The effect of quantizing the network's weights and biases on hardware performance and area is reported. We also conduct design space exploration to compare between design alternatives

47 OTHER INSTRUMENTATION↗