SEARCH · Engineering Papers

Results for “explainable neural networks”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Validation of Image-Based Neural Network Controllersthrough Adaptive Stress Testing

Neural networks have become state-of-the-art for computer vision problems because of their ability to efficiently model complex functions from large amounts of data. While neural networks can be shown to perform well empirically fora variety of tasks, their performance is difficult to guarantee.Neural network verification tools have been developed that can certify robustness with respect to a given input image; however,for neural network systems used in closed-loop controllers,robustness with respect to individual images does not address multi-step properties of the neural network controller and itsenvironment. Furthermore, neural network systems interacting in the physical world and using natural images are operating in a black-box environment, making formal verification in-tractable. This work combines the adaptive stress testing (AST)framework with neural network verification tools to search for the most likely sequence of image disturbances that cause the neural network controlled system to reach a failure. Anautonomous aircraft taxi application is presented, and results show that the AST method finds failures with more likely image disturbances than baseline methods. Further analysis of AST results revealed an explainable cause of the failure, giving insight into the problematic scenarios that should be addressed.

Adaptive Stress Testing, Marabou, Deep Neural Netw↗

NASA NTRSDate not supplied

Understanding and Verifying Neural Networks

Deep Neural Networks (DNNs) have gained immense popularity in recent times and have widespread use in applications such as image classification, sentiment analysis, speech recognition and also in safety-critical applications such as autonomous driving. However, they suffer limitations such as lack of explainability and robustness which raise safety and security concerns in their usage. Further, the complex structure and large input spaces of DNNs act as an impediment to thorough verification and testing. The SafeDNN project at the Robust Software Engineering (RSE) group at NASA aims at exploring techniques to ensure that systems that use deep neural networks are safe, robust and interpretable. In this talk, I will be presenting our technique Prophecy that automatically infers formal properties of deep neural network models. The tool extracts patterns based on neuron activations as preconditions that imply certain desirable output properties of the model. I would be highlighting case studies that use Prophecy in obtaining explanations for network decisions, understanding correct and incorrect behavior, providing formal guarantees wrt safety and robustness, and debugging neural network models. We have applied the tool on image classification networks, neural network controllers providing turn advisories in unmanned aircrafts, regression models used for autonomous center-line tracking in aircrafts and neural network object detectors

Deep Neural Networks↗

NASA NTRS2020

Application of Sparse Identification of Nonlinear Dynamics for Physics-Informed Learning

Advances in machine learning and deep neural networks has enabled complex engineering tasks like image recognition, anomaly detection, regression, and multi-objective optimization, to name but a few. The complexity of the algorithm architecture, e.g., the number of hidden layers in a deep neural network, typically grows with the complexity of the problems they are required to solve, leaving little room for interpreting (or explaining) the path that results in a specific solution. This drawback is particularly relevant for autonomous aerospace and aviation systems, where certifications require a complete understanding of the algorithm behavior in all possible scenarios. Including physics knowledge in such data-driven tools may improve the interpretability of the algorithms, thus enhancing model validation against events with low probability but relevant for system certification. Such events include, for example, spacecraft or aircraft sub-system failures, for which data may not be available in the training phase. This paper investigates a recent physics-informed learning algorithm for identification of system dynamics, and shows how the governing equations of a system can be extracted from data using sparse regression. The learned relationships can be utilized as a surrogate model which, unlike typical data-driven surrogate models, relies on the learned underlying dynamics of the system rather than large number of fitting parameters. The work shows that the algorithm can reconstruct the differential equations underlying the observed dynamics using a single trajectory when no uncertainty is involved. However, the training set size must increase when dealing with stochastic systems, e.g., nonlinear dynamics with random initial conditions.

Corbetta, Matteo↗

NASA NTRS2022

TruePAL – An AI Assistant for First Responder Safety

This paper presents the development of an AI assistant, Trusted and Explainable Artificial Intelligence for Saving Lives (TruePAL), to provide real-time warning of risks of potential crashes to the first responders. The TruePAL system employs an AI and deep learning technology for saving first responders and roadside crews lives in and around active traffic. A deep neural network (DNN) and a Non-Axiomatic Reasoning System (NARS) are implemented as an AI system. A mobile app with AI interface is developed to perform verbal communication with the first responders. The TruePAL team has developed an explainable AI approach by opening up the DNN blackbox to extract the activation filters of various features and parts of the targeted objects. The combination of DNN and NARS makes the TruePAL system explainable to the users. TruePAL ingests on-board cameras, radar, and other sensor signals, analyzes the environment and traffic patterns to generate timely warning to drivers and roadside crews to avoid crashes. The TruePAL team, in collaboration with the Miami/Dade Police Dept., has designed five use cases and multiple sub-scenarios in a CARLA driving simulator to test the capability of TruePAL in timely warning to the first responder drivers in potential crash scenarios. We have successfully demonstrated its capability of timely warning in over a dozen scenarios based on the use cases. The preliminary test simulation results show that TruePAL could provide the drivers and crew members advanced warning before a crash occurs.

Chow, Edward↗

NASA NTRS2005

Training Software in Artificial-Intelligence Computing Techniques

The Artificial Intelligence (AI) Toolkit is a computer program for training scientists, engineers, and university students in three soft-computing techniques (fuzzy logic, neural networks, and genetic algorithms) used in artificial-intelligence applications. The program promotes an easily understandable tutorial interface, including an interactive graphical component through which the user can gain hands-on experience in soft-computing techniques applied to realistic example problems. The tutorial provides step-by-step instructions on the workings of soft-computing technology, whereas the hands-on examples allow interaction and reinforcement of the techniques explained throughout the tutorial. In the fuzzy-logic example, a user can interact with a robot and an obstacle course to verify how fuzzy logic is used to command a rover traverse from an arbitrary start to the goal location. For the genetic algorithm example, the problem is to determine the minimum-length path for visiting a user-chosen set of planets in the solar system. For the neural-network example, the problem is to decide, on the basis of input data on physical characteristics, whether a person is a man, woman, or child. The AI Toolkit is compatible with the Windows 95,98, ME, NT 4.0, 2000, and XP operating systems. A computer having a processor speed of at least 300 MHz, and random-access memory of at least 56MB is recommended for optimal performance. The program can be run on a slower computer having less memory, but some functions may not be executed properly.

Howard, Ayanna↗

NASA NTRS1996

A Comparison of Neural Networks and Fuzzy Logic Methods for Process Modeling

The goal of this work was to analyze the potential of neural networks and fuzzy logic methods to develop approximate response surfaces as process modeling, that is for mapping of input into output. Structural response was chosen as an example. Each of the many methods surveyed are explained and the results are presented. Future research directions are also discussed.

Cios, Krzysztof J.↗

NASA NTRSDate not supplied

Runway Sign Classifier: A DAL C Certifiable Machine Learning System

In recent years, the remarkable progress of Machine Learning (ML) technologies within the domain of Artificial Intelligence (AI) systems has presented unprecedented opportunities for the aviation industry, paving the way for further advancements in automation, including the potential for single pilot or fully autonomous operation of large commercial airplanes. However, ML technology faces major incompatibilities with existing airborne certification standards, such as ML model traceability and explainability issues or the inadequacy of traditional coverage metrics. Certification of ML-based airborne systems using current standards is problematic due to these challenges. This paper presents a case study of an airborne system utilizing a Deep Neural Network (DNN) for airport sign detection and classification. Building upon our previous work, which demonstrates compliance with Design Assurance Level (DAL) ”D”, we upgrade the system to meet the more stringent requirements of Design Assurance Level ”C”. To achieve DAL C, we employ an established architectural mitigation technique involving two redundant and dissimilar Deep Neural Networks. The application of novel ML-specific data management techniques further enhances this approach. This work is intended to illustrate how the certification challenges of ML-based systems can be addressed for medium criticality airborne applications.

Flight Software↗

NASA NTRS1991

Fuzzy expert systems vs. neural networks - Truck backer-upper control revisited

It is pointed out that by merging the advantages of fuzzy expert systems and neural networks one can arrive at a more powerful yet more flexible system for inferencing and learning. The advantages of fuzzy expert systems are their ability to provide nonlinear mapping through the membership functions and fuzzy rules, and the ability to deal with fuzzy information and incomplete and/or imprecise data. The merger of these two concepts is explained using the truck backer-upper control problem. Novel network architectures obtained by merging these two concepts and simulation results for the truck backer-upper problem using the architecture are shown.

Ramamoorthy, P. A.↗

NASA NTRS1998

Emulating the visual receptive-field properties of MST neurons with a template model of heading estimation

We have proposed previously a computational neural-network model by which the complex patterns of retinal image motion generated during locomotion (optic flow) can be processed by specialized detectors acting as templates for specific instances of self-motion. The detectors in this template model respond to global optic flow by sampling image motion over a large portion of the visual field through networks of local motion sensors with properties similar to those of neurons found in the middle temporal (MT) area of primate extrastriate visual cortex. These detectors, arranged within cortical-like maps, were designed to extract self-translation (heading) and self-rotation, as well as the scene layout (relative distances) ahead of a moving observer. We then postulated that heading from optic flow is directly encoded by individual neurons acting as heading detectors within the medial superior temporal (MST) area. Others have questioned whether individual MST neurons can perform this function because some of their receptive-field properties seem inconsistent with this role. To resolve this issue, we systematically compared MST responses with those of detectors from two different configurations of the model under matched stimulus conditions. We found that the characteristic physiological properties of MST neurons can be explained by the template model. We conclude that MST neurons are well suited to support self-motion estimation via a direct encoding of heading and that the template model provides an explicit set of testable hypotheses that can guide future exploration of MST and adjacent areas within the superior temporal sulcus.

NASA Discipline Neuroscience↗

NASA NTRS2002

Single-base-pair discrimination of terminal mismatches by using oligonucleotide microarrays and neural network analyses

The effects of single-base-pair near-terminal and terminal mismatches on the dissociation temperature (T(d)) and signal intensity of short DNA duplexes were determined by using oligonucleotide microarrays and neural network (NN) analyses. Two perfect-match probes and 29 probes having a single-base-pair mismatch at positions 1 to 5 from the 5' terminus of the probe were designed to target one of two short sequences representing 16S rRNA. Nonequilibrium dissociation rates (i.e., melting profiles) of all probe-target duplexes were determined simultaneously. Analysis of variance revealed that position of the mismatch, type of mismatch, and formamide concentration significantly affected the T(d) and signal intensity. Increasing the concentration of formamide in the washing buffer decreased the T(d) and signal intensity, and it decreased the variability of the signal. Although T(d)s of probe-target duplexes with mismatches in the first or second position were not significantly different from one another, duplexes with mismatches in the third to fifth positions had significantly lower T(d)s than those with mismatches in the first or second position. The trained NNs predicted the T(d) with high accuracies (R(2) = 0.93). However, the NNs predicted the signal intensity only moderately accurately (R(2) = 0.67), presumably due to increased noise in the signal intensity at low formamide concentrations. Sensitivity analysis revealed that the concentration of formamide explained most (75%) of the variability in T(d)s, followed by position of the mismatch (19%) and type of mismatch (6%). The results suggest that position of the mismatch at or near the 5' terminus plays a greater role in determining the T(d) and signal intensity of duplexes than the type of mismatch.

Non-NASA Center↗

NASA NTRS1989

Spike train generation and current-to-frequency conversion in silicon diodes

A device physics model is developed to analyze spontaneous neuron-like spike train generation in current driven silicon p(+)-n-n(+) devices in cryogenic environments. The model is shown to explain the very high dynamic range (0 to the 7th) current-to-frequency conversion and experimental features of the spike train frequency as a function of input current. The devices are interesting components for implementation of parallel asynchronous processing adjacent to cryogenically cooled focal planes because of their extremely low current and power requirements, their electronic simplicity, and their pulse coding capability, and could be used to form the hardware basis for neural networks which employ biologically plausible means of information coding.

Coon, D. D.↗

NASA NTRS1999

Textural-Contextual Labeling and Metadata Generation for Remote Sensing Applications

Despite the extensive research and the advent of several new information technologies in the last three decades, machine labeling of ground categories using remotely sensed data has not become a routine process. Considerable amount of human intervention is needed to achieve a level of acceptable labeling accuracy. A number of fundamental reasons may explain why machine labeling has not become automatic. In addition, there may be shortcomings in the methodology for labeling ground categories. The spatial information of a pixel, whether textural or contextual, relates a pixel to its surroundings. This information should be utilized to improve the performance of machine labeling of ground categories. Landsat-4 Thematic Mapper (TM) data taken in July 1982 over an area in the vicinity of Washington, D.C. are used in this study. On-line texture extraction by neural networks may not be the most efficient way to incorporate textural information into the labeling process. Texture features are pre-computed from cooccurrence matrices and then combined with a pixel's spectral and contextual information as the input to a neural network. The improvement in labeling accuracy with spatial information included is significant. The prospect of automatic generation of metadata consisting of ground categories, textural and contextual information is discussed.

Kiang, Richard K.↗

NASA NTRS1991

An introduction to autonomous control systems

The functions, characteristics, and benefits of autonomous control are outlined. An autonomous control functional architecture for future space vehicles that incorporates the concepts and characteristics described is presented. The controller is hierarchical, with an execution level (the lowest level), coordination level (middle level), and management and organization level (highest level). The general characteristics of the overall architecture, including those of the three levels, are explained, and an example to illustrate their functions is given. Mathematical models for autonomous systems, including 'logical' discrete event system models, are discussed. An approach to the quantitative, systematic modeling, analysis, and design of autonomous controllers is also discussed. It is a hybrid approach since it uses conventional analysis techniques based on difference and differential equations and new techniques for the analysis of the systems described with a symbolic formalism such as finite automata. Some recent results from the areas of planning and expert systems, machine learning, artificial neural networks, and the area restructurable controls are briefly outlined.

Antsaklis, Panos J.↗

NASA NTRS1989

Studies with spike initiators - Linearization by noise allows continuous signal modulation in neural networks

It is shown that noise can be an important element in the translation of neuronal generator potentials (summed inputs) to neuronal spike trains (outputs), creating or expanding a range of amplitudes over which the spike rate is proportional to the generator potential amplitude. Noise converts the basically nonlinear operation of a spike initiator into a nearly linear modulation process. This linearization effect of noise is examined in a simple intuitive model of a static threshold and in a more realistic computer simulation of spike initiator based on the Hodgkin-Huxley (HH) model. The results are qualitatively similar; in each case larger noise amplitude results in a larger range of nearly linear modulation. The computer simulation of the HH model with noise shows linear and nonlinear features that were earlier observed in spike data obtained from the VIIIth nerve of the bullfrog. This suggests that these features can be explained in terms of spike initiator properties, and it also suggests that the HH model may be useful for representing basic spike initiator properties in vertebrates.

Yu, Xiaolong↗

NASA NTRS2019

Deep Learning Method for Detecting Precursors to Adverse Events

With the recent advancements in Deep Learning methods, the ability to model large complex heterogeneous data sets are fundamentally changing industry and research. Coupled with hardware improvements, and ease of implementation, a wide variety of deep neural network architectures can quickly be developed to solve a sweeping range of problems such as: object detection in images, automatic healthcare diagnosis using heterogenous data sources, real time language translating and sentence prediction, upscaling low resolution images, and forecasting of multivariate timeseries. Generally, many of these architectures outperform classical machine learning approaches in their respective tasks, however, this typically comes at a cost of interpretability. These black box algorithms generally suffer from lack of transparency in both model complexity as well as the rationale behind the prediction. This lack of comprehension, is driving an emerging area of interest in “Explainable AI”. An algorithm called: “Deep Temporal Multiple Instance Learning”1 was a recently developed to identify precursors to adverse events and has been applied in the aviation domain. The deep learning architecture is designed to capture the evolution of the probability of the outcome over the time preceding the adverse event using a multiple instance learning approach as illustrated in Figure 1. Precursors are defined when the probability of the event has exceeded a threshold at some point in the timeseries, at which point, a sensitivity analysis is performed to determine contributing factors. The contributing factors are used to explain and define the precursor during the periods where the probability score is high. The identified contributing factors are then presented to subject matter experts to provide objective insights into the leading factors associated with the particular adverse event. The algorithm has been tested on flight data from a commercial airline and has the ability to discover precursors to known adverse events that take the form of safety critical operations, such as unstable approach events on final approach. Apart from detecting precursors to adverse events, the converse can also be leveraged to discover corrective actions. These positive actions manifest themselves as periods in the timeseries when the precursor score has been lowered from an elevated state; meaning that if the system had been left uncorrected, it would have eventually reached the adverse event state. Characterizing these state changes can help identify successful interventions that may not have been known before. Policy makers and procedure designers can use this additional knowledge to craft more safety and efficient resilient procedures for future operations and therefore improve the overall performance of the National Airspace.

Matthews, Bryan L.↗

NASA NTRS2020

A Machine Learning Examination of Hydroxyl Radical Differences Among Model Simulations for CCMI-1

Hydroxyl radical (OH) plays critical roles within the troposphere, such as determining the lifetime of methane (CH4), yet is challenging to model due to its fast cycling and dependence on a multitude of sources and sinks. As a result, the reasons for variations in OH and the resulting CH4 lifetime (TCH4), both between models and in time, are difficult to diagnose. We apply a neural network (NN) approach to address this issue within a group of models that participated in the Chemistry-Climate Model Initiative (CCMI). Analysis of the historical specified dynamics simulations performed for CCMI indicates that the primary drivers of TCH4 differences among ten models are the flux of UV light to the troposphere (indicated by the photolysis frequency JO1D) due mostly to clouds, mixing ratio of tropospheric ozone (O3), the abundance of nitrogen oxides (NOx≡NO+NO2), and details of the various chemical mechanisms that drive OH. Water vapor, carbon monoxide (CO), the ratio of NO:NOx, and formaldehyde (HCHO) explain moderate differences in TCH4, while isoprene, CH4, the photolysis frequency of NO2 by visible light (JNO2), overhead O3 column, and temperature account for little-to-no model variation in CH4. We also apply the NNs to analysis of temporal trends in OH from 1980 to 2015. All models that participated in the specified dynamics historical simulation for CCMI demonstrate a decline in CH4 during the analysed timeframe. The significant contributors to this trend, in order of importance, are tropospheric O3, JO1D, NOx, and H2O, with CO also causing substantial interannual variability in OH burden. Finally, the identified trends in TCH4 are compared to calculated trends in the tropospheric mean OH concentration from previous work, based on analysis of observations. The comparison reveals a robust result for the effect of rising water vapor on OH and CH4, imparting an increasing and decreasing trend of about 0.5% decade(exp -1), respectively. The responses due to NOx, O3 column, and temperature are also in reasonably good agreement between the two studies, though a discrepancy in the CH4 response highlights a need for further examination of the CH4 feedback on the abundance of OH.

Julie M Nicely↗

NASA NTRSDate not supplied

Exploring data-driven modeling of boundary layer transition

Prediction of laminar-turbulent transition in boundary layer flows is an important component of predicting the aerodynamic performance of a number of aerospace configurations. According to the CFD Vision 2030 [1], transition modeling represents acriticalarea in CFD simulation capability that will remain a pacing item for the foreseeable future. The fact thattransition can take placevia either one of a myriad possible paths adds to the challenges inreliable transition predictions, despite a limited knowledge of the relevant input parameters. In the low disturbance environments typical of flight applications, transition is often initiated by small amplitude disturbances in the form of linear instability waves of the laminar boundary layer. These disturbances amplify linearly at first and eventually undergo a sequence of nonlinear interactions that result in transition to turbulence. Because the nonlinear phase is rather rapid, the amplification of boundary layer instabilities is governed by the linearstability theory over a majority of the distance leading up to the onset of transition. Semi-empirical transition correlations based on the linear stability theory have been successful in explaining the observed trends in transition location within a broad class of flows. However, the application of stability theory is highly non-robust and often requires a significant domain expertise. Recent work at the NASA Langley Research Center has beenaimed at bridging the gap between physics based transition analyses such as those based on linear stability theory and practical applications that require transition prediction by users that may not be well versed in transition physics. The applications of deep learning have been at the center of these efforts. This presentation will focus on the progress achieved thus far, highlighting the applications of neural networks to selectedtransition scenarios across a range of Mach numbers and flow configuration, as well as the lessons learnedand remaining challengeswithrespect to the selection of training data and neural networks architectures, hyperparameter tuning, and the physical insights distilled from the otherwise black-box models.

M. R. Malik↗

NASA NTRSDate not supplied

Aeroacoustic Characterization of Optimum Hovering Rotors using Artificial Neural Networks

This work illustrates the use of artificial neural network modeling in the aerodynamic and aeroacoustic characterization of optimum hovering rotors over a broad range of design and operating conditions. Design of Experiments was used to create input feature spaces over eight input factors: the number of rotor blades, rotor radius, rotor rotation rate, design thrust condition, collective pitch, airfoil camber, the location of maximum camber, and the airfoil thickness. A low-fidelity tool chain was then used at the discrete data points defined by the designed input feature spaces to analytically design optimum hovering rotors and simulate aerodynamic and aeroacoustic quantities. This allowed for the generation of data sets over which to train and test the artificial neural network prediction models. Prediction models were trained over the data sets for the actual thrust generated by the rotor, power loading, tonal thickness and loading noise at the fundamental blade passage frequency, and broadband self-noise at seventeen one-third octave bands between 1 kHz and 40 kHz. These prediction models were validated by testing over data previously unseen by the models to quantify their capability for generalization to new data within the design feature space. The models were then used to study the effect each input feature had on the aeroacoustics and aerodynamics of optimum hovering rotors and physical insights were concluded to further explain the effect of each input. This characterization study showed that tonal noise and power loading were most sensitive to the number of rotor blades and the rotor rotation rate and that broadband noise was most sensitive to collective pitch and the design thrust condition.

Christopher S Thurman↗