Creating a Culture of Continuous Learning: Solutions for Patient Safety
Explore the source record for details and available documents.
Safety; learning; resilience; safety culture↗
SEARCH · Search NASA
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.
NASA’s System-Wide Safety Project: System-Wide Predictive Analytics and Continuous Learning for In-time Aviation Safety Management Systems (IASMS)
Explore the source record for details and available documents.
Michael James Vincent↗
SUSTAINING NUCLEAR SECURITY REGIMES THROUGH CONTINUOUS LEARNING EXPERIENCES
As Member States plan, implement, and ultimately sustain their nuclear security regimes, human resource development supporting these regimes are paramount. Human resource development broadly includes programs addressing education, training, and knowledge management. The International Atomic Energy Agency’s Implementing Guide, Sustaining a Nuclear Security Regime, highlights the importance of national-level support for assigning resources that help ensure States are able to develop and retain sufficient human resources in the short, medium, and long term. Determining the resources needed to support education, training, and knowledge management is not an easy task, and knowledge management is a practice often overlooked when States plan for and allocate human resources for a nuclear security regime. The paper highlights the importance of implementing knowledge management practices as part of sustaining a nuclear security regime. Given the availability of secure web-based knowledge management tools, a nuclear security human resource development program should not depend solely on direct human interactions. To that end, the paper will offer an approach for planning and implementing a knowledge management system by using the U.S. Department of Energy/National Nuclear Security Administration’s Nuclear Smuggling Detection and Deterrence Knowledge Management Website as a case study. This example offers useful lessons learned for States considering or actively developing their own nuclear security knowledge management efforts and human resource development.
Tremonte, Matthew M.↗
Continual Learning for Particle Accelerators
Explore the source record for details and available documents.
Rajput, Kishansingh [Thomas Jefferson National Acc↗
Neurogenesis Deep Learning: Extending deep networks to accommodate new classes
Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as image and audio processing – data processing domains in which humans have long held clear advantages over conventional algorithms. In contrast to biological neural systems, which are capable of learning continuously, deep artificial networks have a limited ability for incorporating new information in an already trained network. As a result, methods for continuous learning are potentially highly impactful in enabling the application of deep networks to dynamic data sets. Here, inspired by the process of adult neurogenesis in the hippocampus, we explore the potential for adding new neurons to deep layers of artificial neural networks in order to facilitate their acquisition of novel information while preserving previously trained data representations. Our results on the MNIST handwritten digit dataset and the NIST SD 19 dataset, which includes lower and upper case letters and digits, demonstrate that neurogenesis is well suited for addressing the stability-plasticity dilemma that has long challenged adaptive machine learning algorithms.
59 BASIC BIOLOGICAL SCIENCES↗
A Data-Agnostic, Continuous Machine Learning Framework for Application in High Energy Physics and Beyond: Phase 1 Final Scientific/Technical Report
This Phase 1 effort has focused on the development of continual learning frameworks for use in machine learning, specifically in the applied context of High Energy Physics (HEP). Machine learning (ML) is a transformative technology by which computers, typically through the use of neural networks, are able to perform tasks with proficiency that rivals or surpasses that of human users. Model Degradation & Catastrophic Forgetting are two undesired phenomena which can occur in ML where the performance of a model degrades when either deployed on novel data streams, or trained on novel data which are sufficiently different than the data the models were initially trained on. A natural example where these sorts of effects can be observed is in the performance of detectors in harsh environments, where the detector signature may change over the lifetime of the detector as it ages and deteriorates — precisely what occurs in the experiments conducted in HEP. Real world HEP data is therefore an excellent test-ground and use-case for Continual Learning paradigms, which are techniques used in ML to counteract these problems. Ensemble learning is one such technique, where multiple smaller models are trained on subsets of the overall data and are ensembled together during inference. The intuition behind this technique is that, although there are shifts in the distributions which govern the incoming data streams, these shifts are not expected to be homogeneous or global. If a sufficient diversity in solutions within the various sub-models has been achieved, then at least one sub-model is expected to retain its performance within the overall ensemble. One further strength of this approach is that the architectures of the various models do not need to be identical, and in fact even different modalities of data can naturally be combined in this way. This work focused on applying ensemble learning techniques to derive results using two main datasets, anomaly detection in HEP data & time-series forecasting in semiconductor manufacturing data. Semiconductor manufacturing involves data with surprising similarity to that of HEP (e.g. wafer maps look very similar to digi-occupancy maps) and Cerium Lab’s prominence within the semiconductor industry makes semiconductor manufacturing a natural opportunity for commercialization of this work. Our efforts have led to two strong results. The first is that we evaluated the proposed ensembling techniques using previously proposed machine learning architectures for use in anomaly detection, namely AutoEncoder based models and their derivatives. We also developed new architectures which have not been evaluated in this context before. In fact, this work marks the first use of Vision Transformers for anomaly detection in HEP. Second, we demonstrated that ensemble learning significantly improves model performance in scenarios prone to degradation, validating its effectiveness across both HEP and semiconductor datasets. These results further support ensemble learning as a powerful strategy for mitigating catastrophic forgetting and maintaining robust performance in evolving data environments.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Gradient-Based Novelty Detection Boosted by Self-Supervised Binary Classification
Novelty detection aims to automatically identify out-of-distribution (OOD) data, without any prior knowledge of them. It is a critical step in data monitoring, behavior analysis and other applications, helping enable continual learning in the field. Conventional methods of OOD detection perform multi-variate analysis on an ensemble of data or features, and usually resort to the supervision with OOD data to improve the accuracy. In reality, such supervision is impractical as one cannot anticipate the anomalous data. In this paper, we propose a novel, self-supervised approach that does not rely on any pre-defined OOD data: (1) The new method evaluates the Mahalanobis distance of the gradients between the in-distribution and OOD data. (2) It is assisted by a self-supervised binary classifier to guide the label selection to generate the gradients, and maximize the Mahalanobis distance. In the evaluation with multiple datasets, such as CIFAR-10, CIFAR-100, SVHN and TinyImageNet, the proposed approach consistently outperforms state-of-the-art supervised and unsupervised methods in the area under the receiver operating characteristic (AUROC) and area under the precision-recall curve (AUPR) metrics. We further demonstrate that this detector is able to accurately learn one OOD class in continual learning.
Sun, Jingbo↗
Learning in continuous action space for developing high dimensional potential energy models
Reinforcement learning (RL) approaches that combine a tree search with deep learning have found remarkable success in searching exorbitantly large, albeit discrete action spaces, as in chess, Shogi and Go. Many real-world materials discovery and design applications, however, involve multi-dimensional search problems and learning domains that have continuous action spaces. Exploring high-dimensional potential energy models of materials is an example. Traditionally, these searches are time consuming (often several years for a single bulk system) and driven by human intuition and/or expertise and more recently by global/local optimization searches that have issues with convergence and/or do not scale well with the search dimensionality. Here, in a departure from discrete action and other gradient-based approaches, we introduce a RL strategy based on decision trees that incorporates modified rewards for improved exploration, efficient sampling during playouts and a “window scaling scheme" for enhanced exploitation, to enable efficient and scalable search for continuous action space problems. Using high-dimensional artificial landscapes and control RL problems, we successfully benchmark our approach against popular global optimization schemes and state of the art policy gradient methods, respectively. We demonstrate its efficacy to parameterize potential models (physics based and high-dimensional neural networks) for 54 different elemental systems across the periodic table as well as alloys. We analyze error trends across different elements in the latent space and trace their origin to elemental structural diversity and the smoothness of the element energy surface. Broadly, our RL strategy will be applicable to many other physical science problems involving search over continuous action spaces.
36 MATERIALS SCIENCE↗
Convex Q-Learning in Continuous Time with Application to Dispatch of Distributed Energy Resources
Convex Q-learning is a recent approach to reinforcement learning, motivated by the possibility of a firmer theory for convergence, and the possibility of making use of greater a priori knowledge regarding policy or value function structure. This paper explores algorithm design in the continuous time domain, with a finite-horizon optimal control objective. The main contributions are (i) The new Q-ODE: a model-free characterization of the Hamilton-Jacobi-Bellman equation. (ii) A formulation of Convex Q-learning that avoids approximations appearing in prior work. The Bellman error used in the algorithm is defined by filtered measurements, which is necessary in the presence of measurement noise. (iii) Convex Q-learning with linear function approximation is a convex program. It is shown that the constraint region is bounded, subject to an exploration condition on the training input. (iv) The theory is illustrated in application to resource allocation for distributed energy resources, for which the theory is ideally suited.
Lu, Fan↗
Towards continual machine learning for particle accelerators
This talk covers our work on errant beam prognostics at the Spallation Neutron Source (SNS), focusing on the end-to-end process from data collection to the development and deployment of predictive models in specific. A short overview of AIML work done for accelerators and current trends will be presented. We will walk through key steps involved in creating robust Machine Learning (ML) models, including model training, validation, and deployment in an operational setting. In addition to presenting our technical approach, we will share valuable lessons learned, emphasizing the importance of infrastructure to support the continuous adaptation of models to evolving data and system behaviors. This talk will provide insights into the challenges and solutions involved in applying ML to real-world operational environments, with a particular focus on managing data drift and changes in accelerator setup while ensuring model resilience over time.
Accelerator Physics↗
Machine learning for continuous quantum error correction on superconducting qubits
Abstract Continuous quantum error correction has been found to have certain advantages over discrete quantum error correction, such as a reduction in hardware resources and the elimination of error mechanisms introduced by having entangling gates and ancilla qubits. We propose a machine learning algorithm for continuous quantum error correction that is based on the use of a recurrent neural network to identify bit-flip errors from continuous noisy syndrome measurements. The algorithm is designed to operate on measurement signals deviating from the ideal behavior in which the mean value corresponds to a code syndrome value and the measurement has white noise. We analyze continuous measurements taken from a superconducting architecture using three transmon qubits to identify three significant practical examples of non-ideal behavior, namely auto-correlation at temporal short lags, transient syndrome dynamics after each bit-flip, and drift in the steady-state syndrome values over the course of many experiments. Based on these real-world imperfections, we generate synthetic measurement signals from which to train the recurrent neural network, and then test its proficiency when implementing active error correction, comparing this with a traditional double threshold scheme and a discrete Bayesian classifier. The results show that our machine learning protocol is able to outperform the double threshold protocol across all tests, achieving a final state fidelity comparable to the discrete Bayesian classifier.
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
Readiness Evaluation for Sustained Operations
Readiness evaluation for sustained operations is a continuous function that progresses from overseeing establishment of five key programmatic elements during design and construction phases to monitoring the output of those elements performing during commissioning and operations. Continuously assessing readiness for sustained operations becomes an important business function for the U.S. Department of Energy’s Office of River Protection as competition for federal funds increases with increasing waste treatment operations throughout the Office of Environmental Management complex. The five key programmatic elements are as follows: Risk management – Risks and opportunities should prioritize continuous improvement initiatives and be informed by the design and technical authorities and stakeholder monitors. Continuous improvement – All levels of the project organization should exhibit commitment to continuous improvement and learning. Continuity of design and technical authorities – The authorities are responsible for managing knowledge for its effective use in the other elements. Stakeholder monitoring – Active and deliberate monitoring of stakeholder relationships. Sustained operations integrated business planning – Integrated business planning in a federal environment competitive for congressional funding.
12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
Multiclass Continuous Correspondence Learning
We extend the Structural Correspondence Learning (SCL) domain adaptation algorithm of Blitzer er al. to the realm of continuous signals. Given a set of labeled examples belonging to a 'source' domain, we select a set of unlabeled examples in a related 'target' domain that play similar roles in both domains. Using these 'pivot samples, we map both domains into a common feature space, allowing us to adapt a classifier trained on source examples to classify target examples. We show that when between-class distances are relatively preserved across domains, we can automatically select target pivots to bring the domains into correspondence.
correspondence learning↗
Utilizing Reinforcement Learning to Continuously Improve a Primitive-Based Motion Planner
We report in this paper describes how the performance of motion primitive-based planning algorithms can be improved using reinforcement learning. Specifically, we describe and evaluate a framework that autonomously improves the performance of a primitive-based motion planner. The improvement process consists of three phases: exploration, extraction, and reward updates. This process can be iterated continuously to provide successive improvement. The exploration step generates new trajectories, and the extraction step identifies new primitives from these trajectories. These primitives are then used to update rewards for continued exploration. This framework required novel shaping rewards, development of a primitive extraction algorithm, and modification of the Hybrid A* algorithm. The framework is tested on a navigation task using a nonlinear F-16 model. The framework autonomously added 91 motion primitives to the primitive library and reduced average path cost by 21.6 seconds, or 35.75% of the original cost. The learned primitives are applied to an obstacle field navigation task, which was not used in training, and reduced path cost by 16.3 seconds, or 24.1%. Additionally, two heuristics for the modified Hybrid A* algorithm are designed to improve effective branching factor.
42 ENGINEERING↗
The CNSC's Inspector Training and Qualification Program and its Importance to the Nuclear Industry - 19370
Trained, qualified, and designated staff at the Canadian Nuclear Safety Commission (CNSC) conduct inspections of licensed nuclear sites as a method of compliance verification. This paper will describe the unique and comprehensive qualification process for CNSC inspectors, known as the Inspector Training and Qualification Program (ITQP). The ITQP includes service-line-specific training that is unique to each inspection group within the CNSC, dependent on the facility/industry type. The training requirements specific to staff in the Wastes and Decommissioning Division and its impact on safety at waste management sites across Canada will be discussed. This paper will specifically identify the importance of CNSC inspector training and detail how the unique training program requirements enable the CNSC to better identify and encourage compliance among nuclear waste and decommissioning sites in Canada. CNSC inspectors are designated under section 29 of the Nuclear Safety and Control Act (NSCA), and the powers of inspectors are outlined in section 32 of the NSCA. Having trained, qualified, and designated inspectors is paramount for both the CNSC and the nuclear industry. For the CNSC, this ensures that staff in the field are aware of potential hazards and how to mitigate such hazards (if applicable), that staff understand the regulatory framework and how to measure compliance against it, and that staff consistently apply CNSC values across the nuclear industry. For the industry, this ensures that staff present at nuclear facilities are knowledgeable and professional, that inspections are conducted in a consistent manner, and that any compliance actions issued are measurable and defendable against the regulatory framework. The CNSC's ITQP incorporates both theoretical (in-class and online) and practical training, and is broken down into six categories: mandatory training for all new employees; core training; service-line-specific training; on-the-job training; CNSC regulations training; and, recommended additional training. This paper will discuss in detail the specific aspects of each of these categories, the importance of each category including the difference between knowledge and skills acquired in theoretical versus hands-on training, and how CNSC staff in designated inspector positions (inspectors-in-training) progress through the program. The complete list of core training and service-line-specific training for inspectors in the Wastes and Decommissioning Division, including re-qualification requirements, will be explored throughout the paper. It is further important that CNSC designated inspectors undergo continuous learning to ensure that their skills remain up to date, as well as to ensure that inspectors requalify at defined intervals to enable the maintenance of the core knowledge and skills with which the determination of the person's qualification was based. The steps involved in this requalification process, as well as the importance of continuous learning and the maintenance of skills and knowledge will be further discussed. (authors)
12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
Systems and methods for global cyber-attack or fault detection model
An industrial asset may have monitoring nodes that generate current monitoring node values representing a current operation of the industrial asset. An abnormality detection computer may detect when a monitoring node is currently being attacked or experiencing a fault based on a current feature vector, calculated in accordance with current monitoring node values, and a detection model that includes a decision boundary. A model updater (e.g., a continuous learning model updater) may determine an update time-frame (e.g., short-term, mid-term, long-term, etc.) associated with the system based on trigger occurrence detection (e.g., associated with a time-based trigger, a performance-based trigger, an event-based trigger, etc.). The model updater may then update the detection model in accordance with the determined update time-frame (and, in some embodiments, continuous learning).
Xu, Rui↗
Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action
The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) replication transcription complex (RTC) is a multi-domain protein responsible for replicating and transcribing the viral mRNA inside a human cell. Attacking RTC function with pharmaceutical compounds is a pathway to treating COVID-19. Conventional tools, e.g., cryo-electron microscopy and all-atom molecular dynamics (AAMD), do not provide sufficiently high resolution or timescale to capture important dynamics of this molecular machine. Consequently, we develop an innovative workflow that bridges the gap between these resolutions, using mesoscale fluctuating finite element analysis (FFEA) continuum simulations and a hierarchy of AI-methods that continually learn and infer features for maintaining consistency between AAMD and FFEA simulations. We leverage a multi-site distributed workflow manager to orchestrate AI, FFEA, and AAMD jobs, providing optimal resource utilization across HPC centers. Our study provides unprecedented access to study the SARS-CoV-2 RTC machinery, while providing general capability for AI-enabled multi-resolution simulations at scale.
Trifan, Anda↗
Utilizing Reinforcement Learning to Continuously Improve a Primitive-Based Motion Planner.
Abstract not provided.
Goddard, Zachary↗