Lila: Optimal Dispatching in Probabilistic Temporal Networks using Monte Carlo Tree Search
No abstract provided
Chien, Steve A.↗
SEARCH · Search NASA
Results for “tree 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.
VESGEN Software for Mapping and Quantification of Vascular Regulators
VESsel GENeration (VESGEN) Analysis is an automated software that maps and quantifies effects of vascular regulators on vascular morphology by analyzing important vessel parameters. Quantification parameters include vessel diameter, length, branch points, density, and fractal dimension. For vascular trees, measurements are reported as dependent functions of vessel branching generation. VESGEN maps and quantifies vascular morphological events according to fractal-based vascular branching generation. It also relies on careful imaging of branching and networked vascular form. It was developed as a plug-in for ImageJ (National Institutes of Health, USA). VESGEN uses image-processing concepts of 8-neighbor pixel connectivity, skeleton, and distance map to analyze 2D, black-and-white (binary) images of vascular trees, networks, and tree-network composites. VESGEN maps typically 5 to 12 (or more) generations of vascular branching, starting from a single parent vessel. These generations are tracked and measured for critical vascular parameters that include vessel diameter, length, density and number, and tortuosity per branching generation. The effects of vascular therapeutics and regulators on vascular morphology and branching tested in human clinical or laboratory animal experimental studies are quantified by comparing vascular parameters with control groups. VESGEN provides a user interface to both guide and allow control over the users vascular analysis process. An option is provided to select a morphological tissue type of vascular trees, network or tree-network composites, which determines the general collections of algorithms, intermediate images, and output images and measurements that will be produced.
Parsons-Wingerter, Patricia A.↗
Shortcomings with Tree-Structured Edge Encodings for Neural Networks
In evolutionary algorithms a common method for encoding neural networks is to use a tree structured assembly procedure for constructing them. Since node operators have difficulties in specifying edge weights and these operators are execution-order dependent, an alternative is to use edge operators. Here we identify three problems with edge operators: in the initialization phase most randomly created genotypes produce an incorrect number of inputs and outputs; variation operators can easily change the number of input/output (I/O) units; and units have a connectivity bias based on their order of creation. Instead of creating I/O nodes as part of the construction process we propose using parameterized operators to connect to preexisting I/O units. Results from experiments show that these parameterized operators greatly improve the probability of creating and maintaining networks with the correct number of I/O units, remove the connectivity bias with I/O units and produce better controllers for a goal-scoring task.
Hornby, Gregory S.↗
Developing Large-Scale Bayesian Networks by Composition: Fault Diagnosis of Electrical Power Systems in Aircraft and Spacecraft
In this paper, we investigate the use of Bayesian networks to construct large-scale diagnostic systems. In particular, we consider the development of large-scale Bayesian networks by composition. This compositional approach reflects how (often redundant) subsystems are architected to form systems such as electrical power systems. We develop high-level specifications, Bayesian networks, clique trees, and arithmetic circuits representing 24 different electrical power systems. The largest among these 24 Bayesian networks contains over 1,000 random variables. Another BN represents the real-world electrical power system ADAPT, which is representative of electrical power systems deployed in aerospace vehicles. In addition to demonstrating the scalability of the compositional approach, we briefly report on experimental results from the diagnostic competition DXC, where the ProADAPT team, using techniques discussed here, obtained the highest scores in both Tier 1 (among 9 international competitors) and Tier 2 (among 6 international competitors) of the industrial track. While we consider diagnosis of power systems specifically, we believe this work is relevant to other system health management problems, in particular in dependable systems such as aircraft and spacecraft. (See CASI ID 20100021910 for supplemental data disk.)
Mengshoel, Ole Jakob↗
Interpretable Tree-Based and Graph Neural Network Approaches for Novel Solid State Electrolyte Design
All-solid-state batteries with Li metal anode can address the safety issues surrounding traditional Li-ion batteries as well as the demand for higher energy densities. However, the development of solid electrolytes simultaneously possessing high ionic conductivity and good chemical and electrochemical stabilities has proven to be a challenge. I will present our informatics approach to explore the Li compound space for promising solid electrolytes using high-throughput multi-property screening and interpretable machine learning. This is accomplished through the generation of a large database of battery-related materials properties of Li compounds. We use tree-based ensemble learning methods and graph neural network approaches to accurately learn relationships between crystal structures and corresponding thermodynamic and kinetic properties, with interpretability being a major focus. Our models give us the ability to enable rapid discovery and design of novel solid-state battery chemistries.
Materials discovery↗
Algorithm For A Self-Growing Neural Network
CID3 algorithm simulates self-growing neural network. Constructs decision trees equivalent to hidden layers of neural network. Based on ID3 algorithm, which dynamically generates decision tree while minimizing entropy of information. CID3 algorithm generates feedforward neural network by use of either crisp or fuzzy measure of entropy.
Cios, Krzysztof J.↗
Frequency translating phase conjugation circuit for active retrodirective antenna array
An active retrodirective antenna array which has central phasing from a reference antenna element through a "tree" structured network of transmission lines utilizes a number of phase conjugate circuits (PCCs) at each node and a phase reference regeneration circuit (PRR) at each node except the initial node. Each node virtually coincides with an element of the array. A PCC generates the exact conjugate phase of an incident signal using a phase locked loop which combines the phases in an up converter, divides the sum by 2 and mixes the result with the phase in a down converter for phase detection. The PRR extracts the phase from the conjugate phase. Both the PCC and the PRR are not only exact but also free from mixer degeneracy.
Chernoff, R.↗
Automating the multiprocessing environment
An approach to automate the programming and operation of tree-structured networks of multiprocessor systems is discussed. A conceptual, knowledge-based operating environment is presented, and requirements for two major technology elements are identified as follows: (1) An intelligent information translator is proposed for implementating information transfer between dissimilar hardware and software, thereby enabling independent and modular development of future systems and promoting a language-independence of codes and information; (2) A resident system activity manager, which recognizes the systems capabilities and monitors the status of all systems within the environment, is proposed for integrating dissimilar systems into effective parallel processing resources to optimally meet user needs. Finally, key computational capabilities which must be provided before the environment can be realized are identified.
Arpasi, Dale J.↗
Binary tree eigen solver in finite element analysis
This paper presents a transputer-based binary tree eigensolver for the solution of the generalized eigenproblem in linear elastic finite element analysis. The algorithm is based on the method of recursive doubling, which parallel implementation of a number of associative operations on an arbitrary set having N elements is of the order of o(log2N), compared to (N-1) steps if implemented sequentially. The hardware used in the implementation of the binary tree consists of 32 transputers. The algorithm is written in OCCAM which is a high-level language developed with the transputers to address parallel programming constructs and to provide the communications between processors. The algorithm can be replicated to match the size of the binary tree transputer network. Parallel and sequential finite element analysis programs have been developed to solve for the set of the least-order eigenpairs using the modified subspace method. The speed-up obtained for a typical analysis problem indicates close agreement with the theoretical prediction given by the method of recursive doubling.
Akl, F. A.↗
Developing Large-Scale Bayesian Networks by Composition: Fault Diagnosis of Electrical Power Systems in Aircraft and Spacecraft
This CD contains files that support the talk (see CASI ID 20100021404). There are 24 models that relate to the ADAPT system and 1 Excel worksheet. In the paper an investigation into the use of Bayesian networks to construct large-scale diagnostic systems is described. The high-level specifications, Bayesian networks, clique trees, and arithmetic circuits representing 24 different electrical power systems are described in the talk. The data in the CD are the models of the 24 different power systems.
Mengshoel, Ole Jakob↗
VESsel GENeration Analysis (VESGEN): Innovative Vascular Mappings for Astronaut Exploration Health Risks and Human Terrestrial Medicine
Currently, astronauts face significant health risks in future long-duration exploration missions such as colonizing the Moon and traveling to Mars. Numerous risks include greatly increased radiation exposures beyond the low earth orbit (LEO) of the ISS, and visual and ocular impairments in response to microgravity environments. The cardiovascular system is a key mediator in human physiological responses to radiation and microgravity. Moreover, blood vessels are necessarily involved in the progression and treatment of vascular-dependent terrestrial diseases such as cancer, coronary vessel disease, wound-healing, reproductive disorders, and diabetes. NASA developed an innovative, globally requested beta-level software, VESsel GENeration Analysis (VESGEN) to map and quantify vascular remodeling for application to astronaut and terrestrial health challenges. VESGEN mappings of branching vascular trees and networks are based on a weighted multi-parametric analysis derived from vascular physiological branching rules. Complex vascular branching patterns are determined by biological signaling mechanisms together with the fluid mechanics of multi-phase laminar blood flow.
astronaut↗
Supporting Responsible Machine Learning in Heliophysics
Over the last decade, Heliophysics researchers have increasingly adopted a variety of machine learning methods such as artificial neural networks, decision trees, and clustering algorithms into their workflow. Adoption of these advanced data science methods had quickly outpaced institutional response, but many professional organizations such as the European Commission, the National Aeronautics and Space Administration (NASA), and the American Geophysical Union have now issued (or will soon issue) standards for artificial intelligence and machine learning that will impact scientific research. These standards add further (necessary) burdens on the individual researcher who must now prepare the public release of data and code in addition to traditional paper writing. Support for these is not reflected in the current state of institutional support, community practices, or governance systems. We examine here some of these principles and how our institutions and community can promote their successful adoption within the Heliophysics discipline.
Machine learning↗
Climate Controls on Tree Growth in the Western Mediterranean
The first large-scale network of tree-ring chronologies from the western Mediterranean (WM; 32 deg N-43 deg N, 10 deg W-17 deg E) is described and analyzed to identify the seasonal climatic signal in indices of annual ring width. Correlation and rotated empirical orthogonal function analyses are applied to 85 tree-ring series and corresponding gridded climate data to assess the climate signal embedded in the network. Chronologies range in length from 80 to 1129 years. Monthly correlations and partial correlations show overall positive associations for Pinus halepensis (PIHA) and Cedrus atlantica (CDAT) with winter (December-February) and spring (March-May) precipitation across this network. In both seasons, the precipitation correlation with PIHA is stronger, while CDAT chronologies tend to be longer. A combination of positive correlations between growth and winter-summer precipitation and negative partial correlations with growing season temperatures suggests that chronologies in at least part of the network reflect soil moisture and the integrated effects of precipitation and evapotranspiration signal. The range of climate response observed across this network reflects a combination of both species and geographic influences. Western Moroccan chronologies have the strongest association with the North Atlantic Oscillation.
chronology development↗
QuantifyML: How good is my machine learning model?
This paper presents an approach, QuantifyML, which employs model counting to assess the learnability and robustness of machine learning models. Typically the efficacy of machine learning models is determined by computing their accuracy statistically on test data sets. However, this may be misleading, if the test data is not representative of the problem that is being studied. Further, two different models may have the same accuracy on a given data set, measured statistically, but may be very different in their behavior on unseen data. Also, models with high accuracy could have poor adversarial robustness. In QuantifyML, our goal is to precisely quantify the extent to which machine learning models have learned and generalized from the given data. In QuantifyML, a trained model is translated into a C program, which is fed to the CBMC model checking tool to produce a formula in Conjunctive Normal Form (CNF), which in turn is analyzed with state-of-the-art model counters to efficiently obtain precise counts w.r.t different outputs. QuantifyML enables i) evaluating the learnability of models by comparing the counts for the outputs to ground truth, expressed as logical predicates (if available), ii) comparing the performance of different models that may be built with different machine learning algorithms (e.g., decision-trees vs. neural networks), and iii) quantifying the robustness of trained models around given inputs. Our evaluation demonstrates these applications of QuantifyML on decision trees and neural networks trained to learn relational properties of graphs, for which we know the ground truth, and to perform image classification, for which we do not have the ground truth, but we can quantify local robustness.
Deep Neural Networks↗
Computer evaluation of topological formulas for network analysis
Single tree-finding program for digital computer evaluation of topological formulas for network analysis
Chan, S. P.↗
Data fusion with artificial neural networks (ANN) for classification of earth surface from microwave satellite measurements
A data fusion system with artificial neural networks (ANN) is used for fast and accurate classification of five earth surface conditions and surface changes, based on seven SSMI multichannel microwave satellite measurements. The measurements include brightness temperatures at 19, 22, 37, and 85 GHz at both H and V polarizations (only V at 22 GHz). The seven channel measurements are processed through a convolution computation such that all measurements are located at same grid. Five surface classes including non-scattering surface, precipitation over land, over ocean, snow, and desert are identified from ground-truth observations. The system processes sensory data in three consecutive phases: (1) pre-processing to extract feature vectors and enhance separability among detected classes; (2) preliminary classification of Earth surface patterns using two separate and parallely acting classifiers: back-propagation neural network and binary decision tree classifiers; and (3) data fusion of results from preliminary classifiers to obtain the optimal performance in overall classification. Both the binary decision tree classifier and the fusion processing centers are implemented by neural network architectures. The fusion system configuration is a hierarchical neural network architecture, in which each functional neural net will handle different processing phases in a pipelined fashion. There is a total of around 13,500 samples for this analysis, of which 4 percent are used as the training set and 96 percent as the testing set. After training, this classification system is able to bring up the detection accuracy to 94 percent compared with 88 percent for back-propagation artificial neural networks and 80 percent for binary decision tree classifiers. The neural network data fusion classification is currently under progress to be integrated in an image processing system at NOAA and to be implemented in a prototype of a massively parallel and dynamically reconfigurable Modular Neural Ring (MNR).
Lure, Y. M. Fleming↗
Spiking Neurons for Analysis of Patterns
Artificial neural networks comprising spiking neurons of a novel type have been conceived as improved pattern-analysis and pattern-recognition computational systems. These neurons are represented by a mathematical model denoted the state-variable model (SVM), which among other things, exploits a computational parallelism inherent in spiking-neuron geometry. Networks of SVM neurons offer advantages of speed and computational efficiency, relative to traditional artificial neural networks. The SVM also overcomes some of the limitations of prior spiking-neuron models. There are numerous potential pattern-recognition, tracking, and data-reduction (data preprocessing) applications for these SVM neural networks on Earth and in exploration of remote planets. Spiking neurons imitate biological neurons more closely than do the neurons of traditional artificial neural networks. A spiking neuron includes a central cell body (soma) surrounded by a tree-like interconnection network (dendrites). Spiking neurons are so named because they generate trains of output pulses (spikes) in response to inputs received from sensors or from other neurons. They gain their speed advantage over traditional neural networks by using the timing of individual spikes for computation, whereas traditional artificial neurons use averages of activity levels over time. Moreover, spiking neurons use the delays inherent in dendritic processing in order to efficiently encode the information content of incoming signals. Because traditional artificial neurons fail to capture this encoding, they have less processing capability, and so it is necessary to use more gates when implementing traditional artificial neurons in electronic circuitry. Such higher-order functions as dynamic tasking are effected by use of pools (collections) of spiking neurons interconnected by spike-transmitting fibers. The SVM includes adaptive thresholds and submodels of transport of ions (in imitation of such transport in biological neurons). These features enable the neurons to adapt their responses to high-rate inputs from sensors, and to adapt their firing thresholds to mitigate noise or effects of potential sensor failure. The mathematical derivation of the SVM starts from a prior model, known in the art as the point soma model, which captures all of the salient properties of neuronal response while keeping the computational cost low. The point-soma latency time is modified to be an exponentially decaying function of the strength of the applied potential. Choosing computational efficiency over biological fidelity, the dendrites surrounding a neuron are represented by simplified compartmental submodels and there are no dendritic spines. Updates to the dendritic potential, calcium-ion concentrations and conductances, and potassium-ion conductances are done by use of equations similar to those of the point soma. Diffusion processes in dendrites are modeled by averaging among nearest-neighbor compartments. Inputs to each of the dendritic compartments come from sensors. Alternatively or in addition, when an affected neuron is part of a pool, inputs can come from other spiking neurons. At present, SVM neural networks are implemented by computational simulation, using algorithms that encode the SVM and its submodels. However, it should be possible to implement these neural networks in hardware: The differential equations for the dendritic and cellular processes in the SVM model of spiking neurons map to equivalent circuits that can be implemented directly in analog very-large-scale integrated (VLSI) circuits.
Huntsberger, Terrance↗
Portfolios in Stochastic Local Search: Efficiently Computing Most Probable Explanations in Bayesian Networks
Portfolio methods support the combination of different algorithms and heuristics, including stochastic local search (SLS) heuristics, and have been identified as a promising approach to solve computationally hard problems. While successful in experiments, theoretical foundations and analytical results for portfolio-based SLS heuristics are less developed. This article aims to improve the understanding of the role of portfolios of heuristics in SLS. We emphasize the problem of computing most probable explanations (MPEs) in Bayesian networks (BNs). Algorithmically, we discuss a portfolio-based SLS algorithm for MPE computation, Stochastic Greedy Search (SGS). SGS supports the integration of different initialization operators (or initialization heuristics) and different search operators (greedy and noisy heuristics), thereby enabling new analytical and experimental results. Analytically, we introduce a novel Markov chain model tailored to portfolio-based SLS algorithms including SGS, thereby enabling us to analytically form expected hitting time results that explain empirical run time results. For a specific BN, we show the benefit of using a homogenous initialization portfolio. To further illustrate the portfolio approach, we consider novel additive search heuristics for handling determinism in the form of zero entries in conditional probability tables in BNs. Our additive approach adds rather than multiplies probabilities when computing the utility of an explanation. We motivate the additive measure by studying the dramatic impact of zero entries in conditional probability tables on the number of zero-probability explanations, which again complicates the search process. We consider the relationship between MAXSAT and MPE, and show that additive utility (or gain) is a generalization, to the probabilistic setting, of MAXSAT utility (or gain) used in the celebrated GSAT and WalkSAT algorithms and their descendants. Utilizing our Markov chain framework, we show that expected hitting time is a rational function - i.e. a ratio of two polynomials - of the probability of applying an additive search operator. Experimentally, we report on synthetically generated BNs as well as BNs from applications, and compare SGSs performance to that of Hugin, which performs BN inference by compilation to and propagation in clique trees. On synthetic networks, SGS speeds up computation by approximately two orders of magnitude compared to Hugin. In application networks, our approach is highly competitive in Bayesian networks with a high degree of determinism. In addition to showing that stochastic local search can be competitive with clique tree clustering, our empirical results provide an improved understanding of the circumstances under which portfolio-based SLS outperforms clique tree clustering and vice versa.
Mengshoel, Ole J.↗