Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Continual learning”

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

The least constraint principle for learning in neurodynamics

An adaptive neural network for auto-associative memories operating in continuous time is considered. A new learning algorithm for the weight matrix defined by explicit locations of desirable equilibrium points is introduced. The approach is based upon the minimum 'strength energy' of the weight matrix for each prescribed performance of the neural network.

Zak, Michail↗

Evaluation of Strain Measurement Devices for Inflatable Structures

Inflatable structures provide a significant volume savings for future NASA deep space missions. The complexity of these structures, however, provides difficulty for engineers in designing, analyzing, and testing. Common strain measurement systems for metallic parts cannot be used directly on fabrics. New technologies must be developed and tested to accuractly measure the strain of inflatable structures. This paper documents the testing of six candidate strain measurement devices for use on fabrics. The resistance devices tested showed significant hysteresis during creep and cyclic testing. The capacitive device, however, showed excellent results and little-to-no hysteresis. Because of this issue, only two out of the six proposed devices will continue in development. The resulting data and lessons learned from this effort provides direction for continued work to produce a structural health monitoring system for inflatable habitats.

Litteken, Douglas A.↗

Evaluation of Strain Measurement Devices for Inflatable Structures

Inflatable structures provide a significant volume savings for future NASA deep space missions. The complexity of these structures, however, provides difficulty for engineers in designing, analyzing, and testing. Common strain measurement systems for metallic parts cannot be used directly on fabrics. New technologies must be developed and tested to accurately measure the strain of inflatable structures. This paper documents the testing of six candidate strain measurement devices for use on fabrics. The resistance devices tested showed significant hysteresis during creep and cyclic testing. The capacitive device, however, showed excellent results and little-to-no hysteresis. Because of this issue, only two out of the six proposed devices will continue in development. The resulting data and lessons learned from this effort provides direction for continued work to produce a structural health monitoring system for inflatable habitats.

Litteken, Doug↗

Progressive transfer learning for low-frequency data prediction in full waveform inversion

To effectively overcome the cycle-skipping issue in full waveform inversion (FWI), we developed a deep neural network (DNN) approach to predict the absent low-frequency components by exploiting the hidden physical relation connecting the low- and the high-frequency data. To efficiently solve this challenging nonlinear regression problem, two novel strategies were proposed to design the DNN architecture and to optimize the learning process: (1) dual data feed structure; (2) progressive transfer learning. With the dual data feed structure, not only the high-frequency data, but also the corresponding beat tone data are fed into the DNN to relieve the burden of feature extraction. The second strategy, progressive transfer learning, enables us to train the DNN using a single evolving training dataset. Within the framework of the progressive transfer learning, the training dataset continuously evolves in an iterative manner by gradually retrieving the subsurface information through the physics-based inversion module, progressively enhancing the prediction accuracy of the DNN and propelling the inversion process out of the local minima. Here, the synthetic numerical experiments suggest that, without any a priori geological information, the low-frequency data predicted by the progressive transfer learning are sufficiently accurate for an FWI engine to produce reliable subsurface velocity models free of cycle-skipping artifacts.

02 PETROLEUM↗

Loss of Signal, Aeromedical Lessons Learned from the STS-107 Columbia Space Shuttle Mishap

Loss of Signal, a NASA publication to be available in May 2014 presents the aeromedical lessons learned from the Columbia accident that will enhance crew safety and survival on human space flight missions. These lessons were presented to limited audiences at three separate Aerospace Medical Association (AsMA) conferences: in 2004 in Anchorage, Alaska, on the causes of the accident; in 2005 in Kansas City, Missouri, on the response, recovery, and identification aspects of the investigation; and in 2011, again in Anchorage, Alaska, on future implications for human space flight. As we embark on the development of new spacefaring vehicles through both government and commercial efforts, the NASA Johnson Space Center Human Health and Performance Directorate is continuing to make this information available to a wider audience engaged in the design and development of future space vehicles. Loss of Signal summarizes and consolidates the aeromedical impacts of the Columbia mishap process-the response, recovery, identification, investigative studies, medical and legal forensic analysis, and future preparation that are needed to respond to spacecraft mishaps. The goal of this book is to provide an account of the aeromedical aspects of the Columbia accident and the investigation that followed, and to encourage aerospace medical specialists to continue to capture information, learn from it, and improve procedures and spacecraft designs for the safety of future crews. This poster presents an outline of Loss of Signal contents and highlights from each of five sections - the mission and mishap, the response, the investigation, the analysis and the future.

Stepaniak, Phillip C.↗

Loss of Signal, Aeromedical Lessons Learned for the STS-I07 Columbia Space Shuttle Mishap

Loss of Signal, a NASA publication to be available in May 2014, presents the aeromedical lessons learned from the Columbia accident that will enhance crew safety and survival on human space flight missions. These lessons were presented to limited audiences at three separate Aerospace Medical Association (AsMA) conferences: in 2004 in Anchorage, Alaska, on the causes of the accident; in 2005 in Kansas City, Missouri, on the response, recovery, and identification aspects of the investigation; and in 2011, again in Anchorage, Alaska, on future implications for human space flight. As we embark on the development of new spacefaring vehicles through both government and commercial efforts, the NASA Johnson Space Center Human Health and Performance Directorate is continuing to make this information available to a wider audience engaged in the design and development of future space vehicles. Loss of Signal summarizes and consolidates the aeromedical impacts of the Columbia mishap process-the response, recovery, identification, investigative studies, medical and legal forensic analysis, and future preparation that are needed to respond to spacecraft mishaps. The goals of this book are to provide an account of the aeromedical aspects of the Columbia accident and the investigation that followed, and to encourage aerospace medical specialists to continue to capture information, learn from it, and improve procedures and spacecraft designs for the safety of future crews.

Patlach, Robert↗

Spy in the GPU-box: Covert and Side Channel Attacks on Multi-GPU System

The deep learning revolution has been enabled in large part by GPUs, and more recently accelerators, which make it possible to carry out computationally demanding training and inference in acceptable times. As the size of machine learning networks and workloads continues to increase, multi-GPU machines have emerged as an important platform offered on High Performance Computing and cloud data centers. Since these machines are shared among multiple users, it becomes increasingly important to protect applications against potential attacks. In this paper, we explore the vulnerability of Nvidia's DGX multi-GPU machines to covert and side channel attacks. These machines consist of a number of discrete GPUs that are interconnected through a combination of custom interconnect (NVLink) and PCIe connections. We reverse engineer the interconnected cache hierarchy and show that it is possible for an attacker on one GPU to cause contention on the L2 cache of another GPU. We use this observation to first develop a covert channel attack across two GPUs, achieving the best bandwidth of around 4 MB/s. We also develop a prime and probe attack on a remote GPU allowing an attacker to recover the cache access pattern of another workload. This access pattern can be used in any number of side channel attacks: we demonstrate a proof of concept attack that fingerprints the application running on the remote GPU, with high accuracy. We also develop a proof of concept attack to extract hyperparameters of a machine learning workload. Our work establishes for the first time the vulnerability of these machines to microarchitectural attacks and can guide future research to improve their security.

Dutta, Sankha↗

On-policy learning-based deep reinforcement learning assessment for building control efficiency and stability

Artificial intelligence technologies have emerged as a game changer not only in specific applications such as image recognition and machine translation but also in many scientific domains. In particular, as deep reinforcement learning (DRL) has shown great success in complex control problems, DRL-based control has been considered as a potential solution to efficiently control and manage building systems. However, broad assessment of DRL-based building control is still required to characterize their pros and cons in comparison with conventional building control methods (e.g., rule-based feedback controls). In this paper, we assessed DRL-based controls with on-policy learning-based algorithms and continuous control actions for cooling control of large office buildings in the summer season to minimize whole-building energy use and occupant discomfort. We compared DRL-based control methods with two baseline control methods: (1) a pre-determined schedule with supply temperature and static pressure setpoints, and (2) advanced reset method that adjusts setpoints based on heuristic rules, i.e., ASHRAE Guideline 36. We also tested the DRL algorithms to evaluate their performances in multiple climate locations. We found that DRL-based control methods outperformed the baseline control methods in terms of energy savings while maintaining a thermal comfort. DRL reduced energy use between ~4%–22% on average compared to the baseline methods, depending on climate location. We also evaluated DRL-based control in terms of control stability and showed that DRL-based methods should address the span of hardware lifetimes in practical operations.

control stability↗

Self-Evolving Machine: A Continuously Improving Model for Molecular Thermochemistry

Because collecting precise and accurate chemistry data is often challenging, chemistry data sets usually only span a small region of chemical space, which limits the performance and the scope of applicability of data-driven models. To address this issue, we integrated an active learning machine with automatic ab initio calculations to form a self-evolving model that can continuously adapt to new species appointed by the users. In the present work, we demonstrate the self-evolving concept by modeling the formation enthalpies of stable closed-shell polycyclic species calculated at the B3LYP/6-31G(2df,p) level of theory. By combining a molecular graph convolutional neural network with a dropout training strategy, the model we developed can predict density functional theory (DFT) enthalpies for a broad range of polycyclic species and assess the quality of each predicted value. For the species which the current model is uncertain about, the automatic ab initio calculations provide additional training data to improve the performance of the model. For a test set composed of 2858 cyclic and polycyclic hydrocarbons and oxygenates, the enthalpies predicted by the model agree with the reference DFT values with a root-mean-square error of 2.62 kcal/mol. Finally, we found that a model originally trained on hydrocarbons and oxygenates can broaden its prediction coverage to nitrogen-containing species via an active learning process, suggesting that the continuous learning strategy is not only able to improve the model accuracy but is also capable of expanding the predictive capacity of a model to unseen species domains.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Hanford Site Beryllium Program: Past, Present, and Future - 12428

The U.S. Department of Energy (DOE) has a long history of beryllium use because of the element's broad application to many nuclear operations and processes. At the Hanford Site beryllium alloy was used to fabricate parts for reactors, including fuel rods for the N-Reactor during plutonium production. Because of continued confirmed cases of chronic beryllium disease (CBD), and data suggesting CBD occurs at exposures to low-level concentrations, the DOE decided to issue a rule to further protect federal and contractor workers from hazards associated with exposure to beryllium. When the beryllium rule was issued in 1999, each of the Hanford Site contractors developed a Chronic Beryllium Disease Prevention Program (CBDPP) and initial site wide beryllium inventories. A new site-wide CBDPP, applicable to all Hanford contractors, was issued in May, 2009. In the spring of 2010 the DOE Headquarters Office of Health, Safety, and Security (HSS) conducted an independent inspection to evaluate the status of implementation of the Hanford Site Chronic Beryllium Disease Prevention Program (CBDPP). The report identified four Findings and 12 cross-cutting Opportunities for Improvement (OFIs). A corrective action plan (CAP) was developed to address the Findings and crosscutting OFIs. The DOE directed affected site contractors to identify dedicated resources to participate in development of the CAP, along with involving stakeholders. The CAP included general and contractor-specific recommendations. Following initiation of actions to implement the approved CAP, it became apparent that additional definition of product deliverables was necessary to assure that expectations were adequately addressed and CAP actions could be closed. Consequently, a supplement to the original CAP was prepared and transmitted to DOE-HQ for approval. Development of the supplemental CAP was an eight month effort. From the onset a core group of CAP development members were identified to develop a mechanism for assuring that consensus was achieved on products developed as part of the CAP and the closure process. The original CAP was developed based on a large number of actions developed from the HSS report. This was essentially a 'bottoms up' approach. The revised CAP development team concluded that a more holistic, process-based approach was appropriate to assure that the resulting deliverable resulted in a best-in-class product. Consequently, issues and recommendations contained in the HSS report were grouped into 11 program areas, specific product deliverables were identified within each of the program areas, and a work breakdown structure (WBS) was logically applied to number the groupings. While the revised approach to product development utilizes a more holistic, 'top down' approach, the intent was still to incorporate specific recommendations and address specific issues contained in the HSS report. Through implementation of this new approach, a collaborative team has been established that works together using a consensus process for ensuring product completion. Benefits of the new approach include building a level of trust amongst all parties, quality of the products have improved, and acceptance by all parties of what action will truly meet the intent of the deficiency and make the beryllium program stronger. Open dialogue occurs amongst the core Be CAP team members, Hanford contractors, and DOE. It has been a learning process and will continue to be one, but everyone shares the common goal of reducing worker exposure to beryllium. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Structure-aware Initialization via Numerical Continuation and Informed Priors

Scientific machine learning (SciML) often operates in ill-conditioned, weakly identifiable regimes due to limited data or indirect observations. In such settings, optimization and inference are highly sensitive to the starting point, making initialization--often under-reported--a consequential degree of freedom. Random initialization is not a neutral default as it induces an implicit prior over candidate solutions and can systematically bias the result, producing large run-to-run variability. Here, we formalize this view by treating initialization as a hidden confounder in SciML and develop a unifying theory for structure-aware initialization via numerical continuation, constructing warm starts from related problem instances. Across representative tasks, including physics-informed neural networks, maximum likelihood estimation, and variational inference, warm starts have been shown to consistently reduce optimization effort and improve reliability.

Data integrity↗

An Experiment with LLMs as Database Design Tutors: Persistent Equity and Fairness Challenges in Online Learning

As large language models (LLMs) continue to evolve, their capacity to replace humans as their surrogates is also improving. As increasing numbers of intelligent tutoring systems (ITSs) are embracing the integration of LLMs for digital tutoring, questions are arising as to how effective they are and if their hallucinatory behaviors diminish their perceived advantages. One critical question that is seldom asked if the availability, plurality, and relative weaknesses in the reasoning process of LLMs are contributing to the much discussed digital divide and equity and fairness in online learning. In this paper, we present an experiment with database design theory assignments and demonstrate that while their capacity to reason logically is improving, LLMs are still prone to serious errors. We demonstrate that in online learning and in the absence of a human instructor, LLMs could introduce inequity in the form of “wrongful” tutoring that could be devastatingly harmful for learners, which we call ignorant bias, in increasingly popular digital learning. We also show that significant challenges remain for STEM subjects, especially for subjects for which sound and free online tutoring systems exist. Based on the set of use cases, we formulate a possible direction for an effective ITS for online database learning classes of the future.

Jamil, Hasan M. (ORCID:0000000231243780)↗

A machine learning pipeline for membrane segmentation of cryo-electron tomograms

We describe how to use several machine learning techniques organized in a learning pipeline to segment and identify cell membrane structures from cryo electron tomograms. These tomograms are difficult to analyze with traditional segmentation tools. The learning pipeline in our approach starts from supervised learning via a special convolutional neural network trained with simulated data. It continues with semi-supervised reinforcement learning and/or a region merging technique that tries to piece together disconnected components belonging to the same membrane structure. A parametric or non-parametric fitting procedure is then used to enhance the segmentation results and quantify uncertainties in the fitting. Domain knowledge is used in generating the training data for the neural network and in guiding the fitting procedure through the use of appropriately chosen priors and constraints. We demonstrate that the approach proposed here works well for extracting membrane surfaces in two real tomogram datasets.

97 MATHEMATICS AND COMPUTING↗

Intrinsically stretchable neuromorphic devices for on-body processing of health data with artificial intelligence

For leveraging wearable technologies to advance precision medicine, personalized and learning-based analysis of continuously acquired health data is indispensable, for which neuromorphic computing could provide the most efficient implementation of artificial intelligence (AI) data processing. For realizing on-body neuromorphic computing, skin-like stretchability is required, but yet to be combined with the suite of desired neuromorphic metrics, including linear, symmetric weight update, and sufficient state retention, for achieving high computing efficiency. Here, we report an intrinsically stretchable neuromorphic device based on an electrochemical transistor, which provides a large number (>800) of states, linear/symmetric weight update, excellent switching endurance (>100 million), good state retention (>10 4 s), together with high stretchability of 100% strain. Further integration into a prototype array successfully realized the implementation of vector-matrix multiplication even at 100% strain. Finally, we demonstrate the feasibility of implementing AI-based classification of health signals (as exemplified by electrocardiograms) with a high accuracy that is minimally influenced by the stretched state of the neuromorphic hardware. Finally, this work breaks the ground for combining AI data analysis into skin-like wearable electronics for achieving human-integrated/mimetic intelligent systems.

60 APPLIED LIFE SCIENCES↗

Synthesis, optical imaging, and absorption spectroscopy data for 179072 metal oxides

Abstract Optical absorption spectroscopy is an important materials characterization for applications such as solar energy generation. This data descriptor describes the to date (Dec 2018) largest publicly available curated materials science dataset for near infrared to near UV (UV-Vis) light absorbance, composition and processing properties of metal oxides. By supplying the complete synthesis and processing history of each of the 179072 samples from 99965 unique compositions we believe the dataset will enable the community to develop predictive models for materials, such as prediction of optical properties based on composition and processing, and ultimately serve as a benchmark dataset for continued integration of machine learning in materials science. The dataset is also a resource for identifying materials composition and synthesis to attain specific optical properties.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Adaptive Sequential Monte Carlo for Multiple Changepoint Analysis

Process monitoring and control requires detection of structural changes in a data stream in real time. This paper introduces an efficient sequential Monte Carlo algorithm designed for learning unknown changepoints in continuous time. The method is intuitively simple: new changepoints for the latest window of data are proposed by conditioning only on data observed since the most recent estimated changepoint, as these observations carry most of the information about the current state of the process. The proposed method shows improved performance over the current state of the art. Another advantage of the proposed algorithm is that it can be made adaptive, varying the number of particles according to the apparent local complexity of the target changepoint probability distribution. This saves valuable computing time when changes in the changepoint distribution are negligible, and enables re-balancing of the importance weights of existing particles when a significant change in the target distribution is encountered. The plain and adaptive versions of the method are illustrated using the canonical continuous time changepoint problem of inferring the intensity of an inhomogeneous Poisson process, although the method is generally applicable to any changepoint problem. Performance is demonstrated using both conjugate and non-conjugate Bayesian models for the intensity. Lastly, appendices to the article are available online, illustrating the method on other models and applications.

97 MATHEMATICS AND COMPUTING↗

Calibrating Bayesian generative machine learning for Bayesiamplification

Recently, combinations of generative and Bayesian deep learning have been introduced in particle physics for both fast detector simulation and inference tasks. These neural networks aim to quantify the uncertainty on the generated distribution originating from limited training statistics. The interpretation of a distribution-wide uncertainty however remains ill-defined. We show a clear scheme for quantifying the calibration of Bayesian generative machine learning models. For a Continuous Normalizing Flow applied to a low-dimensional toy example, we evaluate the calibration of Bayesian uncertainties from either a mean-field Gaussian weight posterior, or Monte Carlo sampling network weights, to gauge their behaviour on unsteady distribution edges. Well calibrated uncertainties can then be used to roughly estimate the number of uncorrelated truth samples that are equivalent to the generated sample and clearly indicate data amplification for smooth features of the distribution.

97 MATHEMATICS AND COMPUTING↗

Advancing set-conditional set generation: Diffusion models for fast simulation of reconstructed particles

The computational intensity of detector simulation and event reconstruction poses a significant difficulty for data analysis in collider experiments. This challenge inspires the continued development of machine learning techniques to serve as efficient surrogate models. We propose a fast emulation approach that combines simulation and reconstruction. In other words, a neural network generates a set of reconstructed objects conditioned on input particle sets. To make this possible, we advance set-conditional set generation with diffusion models. Using a realistic, generic, and public detector simulation and reconstruction package (COCOA), we show how diffusion models can accurately model the complex spectrum of reconstructed particles inside jets.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗