Search NASA⌕ Search

SEARCH · Search NASA

Results for “algorithm selection”

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 1,621 records · Page 90
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Grain structure and texture selection regimes in metal powder bed fusion

Additive manufacturing (AM) offers opportunities to produce complex part geometries not possible with conventional processing and in some cases even improve part performance. However, adoption has been slowed by difficulties assessing microstructure variability and there is no straightforward approach to relate processing to grain structure characteristics. In this study, datasets from AdditiveFOAM heat transport simulations of laser powder bed fusion (LPBF) are used to drive ExaCA simulations of grain structure. The GPU utilization of ExaCA and an algorithmic update for modeling melt pool overlap region solidification enabled rapid and parallel simulation across a wider range of process conditions than previously explored with cellular automata-based solidification models. A texture selection angle $θ_s$ is defined based on melt pool overlap geometry, and the range of $θ_s$ over which a commonly observed texture transition occurs in characterized AM builds was well-reproduced by ExaCA simulations over a wide range of melt pool shape, hatch spacing, and layer height. ExaCA simulations with 90 degree rotation of the scan direction on every other layer reproduced a number of trends from the AM literature including grain refinement, the dominance of layers with larger melt pools on the final grain structure, and the weakening or strengthening of texture depending on odd and even layer melt pool overlap geometry. EBSD data from a benchmark AM part is used to validate the simulated mechanism of a layer rotation-induced texture strengthening effect. Importantly, these results expand the understanding of the mechanisms for texture selection in alloys with cubic crystal symmetry and offer an approach to easily evaluate processing conditions. With this new understanding, these modeling tools will enable anticipation of previously unexpected variations in grain structure and target specific microstructures and properties.

36 MATERIALS SCIENCE↗
NASA NTRS2015

Magnetospheric Multiscale Instrument Suite Operations and Data System

The four Magnetospheric Multiscale (MMS) spacecraft will collect a combined volume of approximately 100 gigabits per day of particle and field data. On average, only 4 gigabits of that volume can be transmitted to the ground. To maximize the scientific value of each transmitted data segment, MMS has developed the Science Operations Center (SOC) to manage science operations, instrument operations, and selection, downlink, distribution, and archiving of MMS science data sets. The SOC is managed by the Laboratory for Atmospheric and Space Physics (LASP) in Boulder, Colorado and serves as the primary point of contact for community participation in the mission. MMS instrument teams conduct their operations through the SOC, and utilize the SOC's Science Data Center (SOC) for data management and distribution. The SOC provides a single mission data archive for the housekeeping and science data, calibration data, ephemerides, attitude and other ancillary data needed to support the scientific use and interpretation. All levels of data products will reside at and be publicly disseminated from the SDC. Documentation and metadata describing data products, algorithms, instrument calibrations, validation, and data quality will be provided. Arguably, the most important innovation developed by the SOC is the MMS burst data management and selection system. With nested automation and 'Scientist-in-the-Loop' (SITL) processes, these systems are designed to maximize the value of the burst data by prioritizing the data segments selected for transmission to the ground. This paper describes the MMS science operations approach, processes and data systems, including the burst system and the SITL concept.

Baker, D. N.↗
DOE OSTI2019

Face Recognition Algorithm Bias: Performance Differences on Images of Children and Adults

In this work, we examine if current state-of-the-art deep- learning enhanced face recognition systems exhibit a negative bias for children as compared to adults. The systems selected for this work are five top performing1 commercial off-the-shelf (COTS) face recognition systems, two government off-the-shelf (GOTS) face recognition systems and one open-source face recognition solution. The datasets used to evaluate the performance of the systems are both unconstrained in age, pose, illumination, and expression and are publicly available. These datasets are indicative of photo journalistic face datasets published and evaluated on over the last few years. Our findings show a negative bias (i.e., a considerable degradation in performance) for each algorithm on children when compared to the performance obtained on adults. Genuine and imposter distributions high- light the performance bias between the datasets further sup- porting the need for a deeper investigation into algorithm bias as a function of age cohorts. To combat the performance decline on the child demographic, several score- level fusion strategies were evaluated. This work identifies the best score-level fusion technique for child demographic.

Srinivas, Nisha↗
DOE OSTI2018

AUTOMATIC LIMIT SURFACE SEARCH FOR PWR TRANSIENTS BY RELAP5-3D/RAVEN CODES

Deterministic safety analysis of nuclear power plants can be improved by applying modern algorithms and codes exploiting machine learning and parallel computing. In this paper we show the application of some of these advanced methodologies for the determination of limit surfaces. A limit surface is an n-dimensional surface describing the plant status, e.g. identifying, as function of selected plant parameters, the boundaries between failed and safe conditions for the core fuel. Using the RELAP5-3D system thermal-hydraulic code coupled to the RAVEN statistical-analysis code, we show how to apply machine-learning algorithms (near-neighbor, support-vector machine, etc.) for determining relevant limit surfaces for PWR station-blackout and loss of offsite power. As a first step, a set of training simulations is run to sample the nuclear power plant responses. Those calculations are used to train a Reduced-Order-Model (ROM), which RAVEN then uses for determining an approximated limit surface. Verification of the guessed limit surface is then automatically performed and calculation is terminated depending by the chosen convergence criteria. The combination of High Performance Computing (HPC) and ROMs allow a remarkable reduction of the time required for the surface determination. RAVEN performs also the automatic data collection of the output of the numerous runs, thus easing the workload of the safety analyst. Finally, using RAVEN “Ensamble Forward” sampling technique, we show how to inform the limit surface calculations with some of the code and input uncertainties.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS1973

The development of a whole-body algorithm

The whole-body algorithm is envisioned as a mathematical model that utilizes human physiology to simulate the behavior of vital body systems. The objective of this model is to determine the response of selected body parameters within these systems to various input perturbations, or stresses. Perturbations of interest are exercise, chemical unbalances, gravitational changes and other abnormal environmental conditions. This model provides for a study of man's physiological response in various space applications, underwater applications, normal and abnormal workloads and environments, and the functioning of the system with physical impairments or decay of functioning components. Many methods or approaches to the development of a whole-body algorithm are considered. Of foremost concern is the determination of the subsystems to be included, the detail of the subsystems and the interaction between the subsystems.

Kay, F. J.↗
DOE OSTI2024

Phase Selection Rules of Multi‐Principal Element Alloys

Abstract Computational prediction of phase stability of multi‐principal element alloys (MPEAs) holds a lot of promise for rapid exploration of the enormous design space and autonomous discovery of superior structural and functional properties. Regardless of many plausible works that rely on phenomenological theory and machine learning, precise prediction is still limited by insufficient data and the lack of interpretability of some machine learning algorithms, e.g., convolutional neural network. In this work, a comprehensive approach is presented, encompassing the development of a complete dataset that contains 72 387 density functional theory calculations, as well as a predictive global phenomenological descriptor. The phase selection descriptor, based on atomic electronegativity and valence electron concentration, significantly outperforms the widely used valence electron concentration, excelling in both accuracy (with an f1 score of 63% compared to 47%) and its ability to predict the HCP phase (0.48 recall compared to 0). The comprehensive data mining on the global design space of 61 425 quaternary MPEAs made from 28 possible metals, together with the phenomenological theory and physical interpretation, will set up a solid computational science foundation for data‐driven exploration of MPEAs.

Chemistry↗
NASA NTRS2009

Regression Model Optimization for the Analysis of Experimental Data

A candidate math model search algorithm was developed at Ames Research Center that determines a recommended math model for the multivariate regression analysis of experimental data. The search algorithm is applicable to classical regression analysis problems as well as wind tunnel strain gage balance calibration analysis applications. The algorithm compares the predictive capability of different regression models using the standard deviation of the PRESS residuals of the responses as a search metric. This search metric is minimized during the search. Singular value decomposition is used during the search to reject math models that lead to a singular solution of the regression analysis problem. Two threshold dependent constraints are also applied. The first constraint rejects math models with insignificant terms. The second constraint rejects math models with near-linear dependencies between terms. The math term hierarchy rule may also be applied as an optional constraint during or after the candidate math model search. The final term selection of the recommended math model depends on the regressor and response values of the data set, the user s function class combination choice, the user s constraint selections, and the result of the search metric minimization. A frequently used regression analysis example from the literature is used to illustrate the application of the search algorithm to experimental data.

Ulbrich, N.↗
NASA NTRS2022

Merging of the Case 2 Regional Coast Colour and Maximum‑Peak Height Chlorophyll‑a Algorithms: Validation and Demonstration of Satellite‑derived Retrievals Across US Lakes

Water quality monitoring is relevant for protecting the designated, or beneficial uses, of water such as drinking, aquatic life, recreation, irrigation, and food supply that support the economy, human well-being, and aquatic ecosystem health. Managing finite water resources to support these designated uses requires information on water quality so that managers can make sustainable decisions. Chlorophyll-a (chl-a, µg L−1) concentration can serve as a proxy for phytoplankton biomass and may be used as an indicator of increased anthropogenic nutrient stress. Satellite remote sensing may present a complement to in situ measures for assessments of water quality through the retrieval of chl-a with in-water algorithms. Validation of chl-a algorithms across US lakes improves algorithm maturity relevant for monitoring applications. This study compares performance of the Case 2 Regional Coast Colour (C2RCC) chl-a retrieval algorithm, a revised version of the Maximum-Peak Height (MPH(P)) algorithm, and three scenarios merging these two approaches. Satellite data were retrieved from the MEdium Resolution Imaging Spectrometer (MERIS) and the Ocean and Land Colour Instrument (OLCI), while field observations were obtained from 181 lakes matched with U.S. Water Quality Portal chl-a data. The best performance based on mean absolute multiplicative error (MAEmult) was demonstrated by the merged algorithm referred to as C15−M10 (MAEmult = 1.8, biasmult = 0.97, n = 836). In the C15−M10 algorithm, the MPH(P) chl-a value was retained if it was > 10 µg L−1; if the MPH(P) value was ≤ 10 µg L−1, the C2RCC value was selected, as long as that value was < 15 µg L−1. Time-series and lake-wide gradients compared against independent assessments from Lake Champlain and long-term ecological research stations in Wisconsin were used as complementary examples supporting water quality reporting requirements. Trophic state assessments for Wisconsin lakes provided examples in support of inland water quality monitoring applications. This study presents and assesses merged adaptations of chl-a algorithms previously reported independently. Additionally, it contributes to the transition of chl-a algorithm maturity by quantifying error statistics for a number of locations and times.

Satellite↗
NASA NTRS2014

An Evaluation of a Flight Deck Interval Management Algorithm Including Delayed Target Trajectories

NASA's first Air Traffic Management (ATM) Technology Demonstration (ATD-1) was created to facilitate the transition of mature air traffic management technologies from the laboratory to operational use. The technologies selected for demonstration are the Traffic Management Advisor with Terminal Metering (TMA-TM), which provides precise timebased scheduling in the terminal airspace; Controller Managed Spacing (CMS), which provides controllers with decision support tools enabling precise schedule conformance; and Interval Management (IM), which consists of flight deck automation that enables aircraft to achieve or maintain precise in-trail spacing. During high demand operations, TMA-TM may produce a schedule and corresponding aircraft trajectories that include delay to ensure that a particular aircraft will be properly spaced from other aircraft at each schedule waypoint. These delayed trajectories are not communicated to the automation onboard the aircraft, forcing the IM aircraft to use the published speeds to estimate the target aircraft's estimated time of arrival. As a result, the aircraft performing IM operations may follow an aircraft whose TMA-TM generated trajectories have substantial speed deviations from the speeds expected by the spacing algorithm. Previous spacing algorithms were not designed to handle this magnitude of uncertainty. A simulation was conducted to examine a modified spacing algorithm with the ability to follow aircraft flying delayed trajectories. The simulation investigated the use of the new spacing algorithm with various delayed speed profiles and wind conditions, as well as several other variables designed to simulate real-life variability. The results and conclusions of this study indicate that the new spacing algorithm generally exhibits good performance; however, some types of target aircraft speed profiles can cause the spacing algorithm to command less than optimal speed control behavior.

Swieringa, Kurt A.↗
DOE OSTI2021

Machine learning based algorithms for uncertainty quantification in numerical weather prediction models

Complex numerical weather prediction models incorporate a variety of physical processes, each described by multiple alternative physical schemes with specific parameters. The selection of the physical schemes and the choice of the corresponding physical parameters during model configuration can significantly impact the accuracy of model forecasts. There is no combination of physical schemes that works best for all times, at all locations, and under all conditions. It is therefore of considerable interest to understand the interplay between the choice of physics and the accuracy of the resulting forecasts under different conditions. This paper demonstrates the use of machine learning techniques to study the uncertainty in numerical weather prediction models due to the interaction of multiple physical processes. The first problem addressed herein is the estimation of systematic model errors in output quantities of interest at future times, and the use of this information to improve the model forecasts. The second problem considered is the identification of those specific physical processes that contribute most to the forecast uncertainty in the quantity of interest under specified meteorological conditions. In order to address these questions we employ two machine learning approaches, random forests and artificial neural networks. The discrepancies between model results and observations at past times are used to learn the relationships between the choice of physical processes and the resulting forecast errors. Numerical experiments are carried out with the Weather Research and Forecasting (WRF) model. The output quantity of interest is the model precipitation, a variable that is both extremely important and very challenging to forecast. The physical processes under consideration include various micro-physics schemes, cumulus parameterizations, short wave, and long wave radiation schemes. The experiments demonstrate the strong potential of machine learning approaches to aid the study of model errors.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

The PSZ-MCMF catalogue of Planck clusters over the DES region

ABSTRACT We present the first systematic follow-up of Planck Sunyaev–Zeldovich effect (SZE) selected candidates down to signal-to-noise (S/N) of 3 over the 5000 deg2 covered by the Dark Energy Survey. Using the MCMF cluster confirmation algorithm, we identify optical counterparts, determine photometric redshifts, and richnesses and assign a parameter, fcont, that reflects the probability that each SZE-optical pairing represents a random superposition of physically unassociated systems rather than a real cluster. The new PSZ-MCMF cluster catalogue consists of 853 MCMF confirmed clusters and has a purity of 90 per cent. We present the properties of subsamples of the PSZ-MCMF catalogue that have purities ranging from 90 per cent to 97.5 per cent, depending on the adopted fcont threshold. Halo mass estimates M500, redshifts, richnesses, and optical centres are presented for all PSZ-MCMF clusters. The PSZ-MCMF catalogue adds 589 previously unknown Planck identified clusters over the DES footprint and provides redshifts for an additional 50 previously published Planck-selected clusters with S/N>4.5. Using the subsample with spectroscopic redshifts, we demonstrate excellent cluster photo-z performance with an RMS scatter in Δz/(1 + z) of 0.47 per cent. Our MCMF based analysis allows us to infer the contamination fraction of the initial S/N>3 Planck-selected candidate list, which is ∼50 per cent. We present a method of estimating the completeness of the PSZ-MCMF cluster sample. In comparison to the previously published Planck cluster catalogues, this new S/N>3 MCMF confirmed cluster catalogue populates the lower mass regime at all redshifts and includes clusters up to z∼1.3.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2009

Highly Scalable Matching Pursuit Signal Decomposition Algorithm

Matching Pursuit Decomposition (MPD) is a powerful iterative algorithm for signal decomposition and feature extraction. MPD decomposes any signal into linear combinations of its dictionary elements or atoms . A best fit atom from an arbitrarily defined dictionary is determined through cross-correlation. The selected atom is subtracted from the signal and this procedure is repeated on the residual in the subsequent iterations until a stopping criterion is met. The reconstructed signal reveals the waveform structure of the original signal. However, a sufficiently large dictionary is required for an accurate reconstruction; this in return increases the computational burden of the algorithm, thus limiting its applicability and level of adoption. The purpose of this research is to improve the scalability and performance of the classical MPD algorithm. Correlation thresholds were defined to prune insignificant atoms from the dictionary. The Coarse-Fine Grids and Multiple Atom Extraction techniques were proposed to decrease the computational burden of the algorithm. The Coarse-Fine Grids method enabled the approximation and refinement of the parameters for the best fit atom. The ability to extract multiple atoms within a single iteration enhanced the effectiveness and efficiency of each iteration. These improvements were implemented to produce an improved Matching Pursuit Decomposition algorithm entitled MPD++. Disparate signal decomposition applications may require a particular emphasis of accuracy or computational efficiency. The prominence of the key signal features required for the proper signal classification dictates the level of accuracy necessary in the decomposition. The MPD++ algorithm may be easily adapted to accommodate the imposed requirements. Certain feature extraction applications may require rapid signal decomposition. The full potential of MPD++ may be utilized to produce incredible performance gains while extracting only slightly less energy than the standard algorithm. When the utmost accuracy must be achieved, the modified algorithm extracts atoms more conservatively but still exhibits computational gains over classical MPD. The MPD++ algorithm was demonstrated using an over-complete dictionary on real life data. Computational times were reduced by factors of 1.9 and 44 for the emphases of accuracy and performance, respectively. The modified algorithm extracted similar amounts of energy compared to classical MPD. The degree of the improvement in computational time depends on the complexity of the data, the initialization parameters, and the breadth of the dictionary. The results of the research confirm that the three modifications successfully improved the scalability and computational efficiency of the MPD algorithm. Correlation Thresholding decreased the time complexity by reducing the dictionary size. Multiple Atom Extraction also reduced the time complexity by decreasing the number of iterations required for a stopping criterion to be reached. The Course-Fine Grids technique enabled complicated atoms with numerous variable parameters to be effectively represented in the dictionary. Due to the nature of the three proposed modifications, they are capable of being stacked and have cumulative effects on the reduction of the time complexity.

Christensen, Daniel↗
DOE OSTI2021

Gradient-Informed Design Optimization of Select Nuclear Systems

In this work, we present a gradient-informed design optimization of nuclear reactor core components based on neutronics objectives with both continuous and discrete materials. The main argument in favor of using gradient-informed design optimization is that it scales well with increasing dimensionality of the design space. First, a challenge problem with 121 free parameters is solved with a gradient-informed method and then with a genetic algorithm. Then, a challenge problem to optimize the flux profile of a simplified assembly with eight axial zones is solved. Both challenge problems are solved using directly calculated derivatives from Tools for Sensitivity and Uncertainty Analysis Methodology Implementation (TSUNAMI) in the SCALE package. Furthermore, we demonstrate how a discrete optimization problem—selection of materials for 121 voxels—can be lifted into a continuous problem with mixed materials. In the continuous space, adjoint-based gradients are well-defined, and gradient descent is applicable. Then, a forcing function is introduced that with the selection of an appropriately sized hyperparameter can be used to guide the optimized continuous solution back into a discrete solution. This paper presents an account of the challenges that were faced when applying a gradient-informed optimization algorithm using a Monte Carlo calculation to estimate the gradient information and compares a gradient descent optimization method to a genetic algorithm optimization of the same geometry. Overall, this work demonstrates the potential use of adjoint-based gradient calculations in design optimization of nuclear systems.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2018

Improved Nested Sampling and Surrogate-Enabled Comparison With Other Marginal Likelihood Estimators

Estimating marginal likelihood is of central importance to Bayesian model selection and/or model averaging. The nested sampling method has been recently used together with the Metropolis-Hasting (M-H) sampling algorithm for estimating marginal likelihood. This study develops a new implementation of nested sampling by using the DiffeRential Evolution Adaptive Metropolis (DREAMzs) sampling algorithm. The two implementations of nested sampling are evaluated for four models of a synthetic groundwater flow modeling. The DREAMzs-based nested sampling outperforms the M-H-based nested sampling in terms of their accuracy, convergence, efficiency, and stability, which is attributed to the fact that DREAMzs is more robust than M-H for parameter sampling. The nested sampling method is also compared with four other methods (arithmetic mean, harmonic mean, stabilized harmonic mean, and thermodynamic integration) commonly used for estimating marginal likelihood and posterior probability of the four groundwater models. The comparative study requires hundreds of millions of model executions, which would not be possible without using surrogate models to replace the original models. Using the arithmetic mean estimator as the reference, the comparison reveals that thermodynamic integration outperforms nested sampling in terms of accuracy and stability, whereas nested sampling is more computationally efficient to reach to convergence. Here, the harmonic mean and stabilized harmonic mean methods give the worst marginal likelihood estimation. Accurate marginal likelihood estimation is important for accurate estimation of posterior model probability and better predictive performance of Bayesian model averaging.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Localized keyhole pore prediction during laser powder bed fusion via multimodal process monitoring and X-ray radiography

Systematic fault detection and control during laser powder bed fusion (L-PBF) has been a long-standing objective for system manufacturers and researchers in the additive manufacturing (AM) industry. This manuscript investigates a data fusion approach for detection of keyhole porosity formation during laser irradiation of Ti-6Al-4V substrates by concurrent recording of thermally induced optical emission measured using both off-axis and coaxial photodiode sensors, and acoustic emission. Subsurface defect formation was monitored via high-speed synchrotron X-ray imaging at 20,000 frames per second, enabling temporal registration of keyhole pore formation events to the monitoring signals at a resolution of 50 µs. We developed data fusion machine learning (ML) models for localized prediction of keyhole pore formation at various time scales ranging from 0.5 ms to 2 ms. The signal segments were featurized using two independent approaches: (1) power spectral density (PSD) and (2) highly comparative time series analysis (HCTSA) framework. The extracted features from different sensor modalities were fused together to construct a multimodal feature space and sequential feature selection was used to determine the most informative features for training the ML models. The predictive performance was evaluated for three classifying algorithms: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Gaussian Naive Bayes (GNB). As a result, pore formation events were predicted with up to 0.95 F1-score, 1.0 recall and 0.94 accuracy. The most heavily weighted features indicate that model performance is chiefly governed by the acoustic monitoring signal, with a secondary contribution from the optical emission sensors.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Parton distribution functions from scalar light-front parton gas model

Here, we propose an application of a microcanonical ensemble with light-front kinematics to model the phase-space distribution of relativistic constituents of a bound state. These constituents denoted by partons are treated as classical spin-zero particles confined inside the bound state with inter-parton collisions as their only interaction. The microcanonical molecular dynamics ensemble is applied to obtain the phase-space distribution of such a thermodynamic system. We sample this phase-space distribution using Monte Carlo algorithms to obtain the parton distribution functions (PDFs) in scenarios with 3, 4, and 5 identical partons. In addition PDFs when a selected number of massless partons are mixed with 3 massive partons are also presented.

Microcanonical ensemble↗
DOE OSTI2018

A New Global Storage-Area-Depth Data Set for Modeling Reservoirs in Land Surface and Earth System Models

Reservoir storage-area-depth relationships are the most important factors controlling thermal stratification in reservoirs and, more broadly, the water, energy and biogeochemical dynamics in the reservoirs and subsequently their impacts on downstream rivers. However, most land surface or earth system models do not account for the gradual changes of reservoir surface area and storage with the changing depth, inhibiting a consistent and accurate representation of mass, energy and biogeochemical balances in reservoirs. Here we present a physically coherent parameterization of reservoir storage-area-depth dataset at the global scale. For each reservoir, the storage-area-depth relationships were derived from an optimal geometric shape selected iteratively from five possible regular geometric shapes that minimizes the error of total storage and surface area estimation. We applied this algorithm to 6,800 reservoirs included in the Global Reservoir and Dam database (GRanD). The relative error between the estimated and observed total storage is no more than 5% and 50% for 66% and 99% of all GRanD reservoirs, respectively. More importantly, the storage-depth profiles derived from the approximated reservoir geometry compared well with remote sensing based estimation at 40 major reservoirs from previous studies, and ground-truth measurements for 34 reservoirs in the United States and China. Furthermore, the new global reservoir storage-area-depth dataset is critical for advancing future modeling and understanding of reservoir processes and subsequent effects on the terrestrial hydrological, ecological and biogeochemical cycles at the regional and global scales.

13 HYDRO ENERGY↗
DOE OSTI2019

Visualization System for Evolutionary Neural Networks for Deep Learning

Deep learning is actively used in a wide range of fields for scientific discovery. To effectively apply deep learning to a particular problem, it is important to select an appropriate network architecture and other hyper-parameters (at each layer). Evolving architectures and hyper-parameters using a genetic algorithm is one current approach to search the huge space of all possible configurations to find those more optimal for the problem. However, examining an evolutionary process and tuning the genetic algorithm are challenging, pushing most users to treat the process as a black box. To address this challenge, we propose a visualization system for evolutionary neural networks for deep learning. The key feature of our visualization system is to provide a visual analytics environment for evaluating a genetic algorithm in order to improve the underlying operations to reduce time to find good solutions. Our system is able to not only visualize how a genetic algorithm traverses its search space but also allows users to examine evolving networks in-depth to get insights to improve performance through interactive visualization components.

Chae, Junghoon↗