Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “train”

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 109 records · Page 6

Best Practices for NERSC Training

The National Energy Research Supercomputing Center (NERSC) at Lawrence Berkeley National Laboratory (LBNL) organizes approximately 20 training events per year for its 8,000 users from 800 projects, who have varying levels of High Performance Computing (HPC) knowledge and familiarity with NERSC's HPC resources. Due to the novel circumstances of the pandemic, NERSC began transforming our traditional smaller-scale, on-site training events to larger-scale, fully virtual sessions in March 2020. We treated this as an opportunity to try new approaches and improve our training best practices. This paper describes the key practices we have developed since the start of this transformation, including considerations for organizing events; collaboration with other HPC centers and the DOE ECP Program to increase reach and impact of events; targeted emails to users to increase attendance; efficient management of user accounts for computational resource access; strategies for preventing Zoombombing; streamlining the publication of professional-quality, closed-captioned videos on the NERSC YouTube channel for accessibility; effective communication channels for Q&A; tailoring training contents to NERSC user needs via close collaboration with vendors and presenters; standardized training procedures and publishing of training materials; and considerations for planning HPC training topics. Additionally, most of these practices will be continued after the pandemic as effective norms for training.

97 MATHEMATICS AND COMPUTING↗

FAST MAGNETOACOUSTIC WAVE TRAINS OF SAUSAGE SYMMETRY IN CYLINDRICAL WAVEGUIDES OF THE SOLAR CORONA

Fast magnetoacoustic waves guided along the magnetic field by plasma non-uniformities, in particular coronal loops, fibrils, and plumes, are known to be highly dispersive, which lead to the formation of quasi-periodic wave trains excited by a broadband impulsive driver, e.g., a solar flare. We investigated the effects of cylindrical geometry on the fast sausage wave train formation. We performed magnetohydrodynamic numerical simulations of fast magnetoacoustic perturbations of a sausage symmetry, propagating from a localized impulsive source along a field-aligned plasma cylinder with a smooth radial profile of the fast speed. The wave trains are found to have pronounced period modulation, with the longer instant period seen in the beginning of the wave train. The wave trains also have a pronounced amplitude modulation. Wavelet spectra of the wave trains have characteristic tadpole features, with the broadband large-amplitude heads preceding low-amplitude quasi-monochromatic tails. The mean period of the wave train is about the transverse fast magnetoacoustic transit time across the cylinder. The mean parallel wavelength is about the diameter of the wave-guiding plasma cylinder. Instant periods are longer than the sausage wave cutoff period. The wave train characteristics depend on the fast magnetoacoustic speed in both the internal and external media, the smoothness of the transverse profile of the equilibrium quantities, and also the spatial size of the initial perturbation. If the initial perturbation is localized at the axis of the cylinder, the wave trains contain higher radial harmonics that have shorter periods.

79 ASTRONOMY AND ASTROPHYSICS↗

Fair Concurrent Training of Multiple Models in Federated Learning

Federated learning (FL) enables collaborative learning across multiple clients. In most FL work, all clients train a single learning task. However, the recent proliferation of FL applications may increasingly require multiple FL tasks to be trained simultaneously, sharing clients’ computing resources, which we call Multiple-Model Federated Learning (MMFL). Current MMFL algorithms use naïve average-based client-task allocation schemes that often lead to unfair performance when FL tasks have heterogeneous difficulty levels, as the more difficult tasks may need more client participation to train effectively. Furthermore, in the MMFL setting, we face a further challenge that some clients may prefer training specific tasks to others, and may not even be willing to train other tasks, e.g., due to high computational costs, which may exacerbate unfairness in training outcomes across tasks. We address both challenges by firstly designing FedFairMMFL, a difficulty-aware algorithm that dynamically allocates clients to tasks in each training round, based on the tasks’ current performance levels. We provide guarantees on the resulting task fairness and FedFairMMFL’s convergence rate. We then propose novel auction designs that incentivizes clients to train multiple tasks, so as to fairly distribute clients’ training efforts across the tasks, and extend our convergence guarantees to this setting. Here, we finally evaluate our algorithm with multiple sets of learning tasks on real world datasets, showing that our algorithm improves fairness by improving the final model accuracy and convergence speed of the worst performing tasks, while maintaining the average accuracy across tasks.

Federated learning↗

Training data selection for event classification in a highly variable environment

A problem of interest for nuclear nonproliferation is monitoring activities at nuclear facilities, where proliferation events may only take place a few times and often under variable conditions. Machine learning has revolutionized data analytics by enabling the use of measurable signatures to generate predictive models of facility operations. However, traditional methods for training these models require large, reliable data sets with labeled observations, a challenge for nonproliferation. Highly variable conditions further complicate this as events from training data may have occurred in conditions quite different from the event of interest. Our hypothesis is that when events occur in a highly variable environment, careful training data selection for each test event could outperform the standard approach of using all available training data. We developed a method to optimize training data selection for the given test event and applied it to predicting the power level of the High Flux Isotope Reactor (HFIR) at Oak Ridge National Laboratory. In this study, the reactor startup exhibits variability between occurrences due to natural variability in environmental conditions and operational procedures. Using a combination of analysis techniques, a similitude assessment was performed on data collected from HFIR to isolate clusters that were optimal for training a predictive model. Concepts such as dynamic time warping and Jaccard similarity were used in conjunction with clustering analysis. In order to validate this approach, the model was trained on every combination of unique training events and the predictive performance was compared to the performance using a subset of the training data selected by isolated clusters found through the similitude assessment.

Iyer, A↗

How Good is Good Enough?: Quantifying the Effects of Training Set Quality

There is a general consensus in the neural network community that noise in training data has a negative impact on model output; however, efforts to quantify the impact of varying levels have been limited, particularly for semantic segmentation tasks. This is a question of particular importance for remote sensing applications where the cost of producing a large training set can lead to reliance on publicly available data with varying degrees of noise. This work explores the effects of different degrees and types of training label noise on a pre-trained building extraction deep learner. Quantitative and qualitative evaluations of these effects can help inform decisions about trade-offs between the cost of producing training data and the quality of model outputs. We found that, relative to the base model, models trained with small amounts of noise showed little change in precision but achieved considerable increases in recall. Conversely, as noise levels increased, both precision and recall decreased. Precision and recall both lagged behind a model trained with pristine data. These exploratory results indicate the importance of quality control for training and, more broadly, that the relationship between degrees and types of training data noise and model performance is more complex than trade-offs between precision and recall.

Swan, Benjamin↗

FINAL SCIENTIFIC REPORT Southwest United States of America – Distributed Technology Training Consortia (SWUSA-DTTC) Contract Number: DE-EE0006339

The Southwest United States of America – Distributed Technology Training Consortia (SWUSA-DTTC) leveraged the highest concentration of renewable resources in the U.S. as well as operation of the leading independent microgrid installations and other distributed technologies to collect and analyze real-time data streams, advance power system simulations and analysis, identify educational and training gaps and develop solutions-focused curricula. The SWUSA-DTTC consortium posed a unique collaboration between universities and utilities to ensure that classes were focused on subjects and topics of interest to the utilities and ones that had practical benefit related to the preparedness for accommodating high penetration of solar and other distributed energy technologies. This approach to have a close collaboration and shared effort to develop the course content and curriculum is unique and a significant departure from conventional course development. This coursework and training was intended to endure over a long time horizon (10-20 year time frame), and include professionals over the entire Southwest region and the rest of the US, and even outreach into foreign countries. Project Objectives In order to support the increase in power systems research, development, and analytical capacity, the SWUSA-DTTC brought together respected professors in Power Systems education, student/professor research and development, and valuable industry and utility experience. Through this program, the partnered universities created and/or modified existing curricula available to students and professionals in the form of university courses, short courses, videos, consortia-led training, and online materials. During this time, the supporting vendors and utilities provided the SWUSA-DTTC with technical advisory roles as well as providing input and feedback in terms of utility and related energy industry needs. The goals were to create power and energy systems training, curricula, and workforce preparedness through the inclusion of data collection and analysis, power systems expertise, and application-specific training activities which build on fundamental principles, modeling and simulation tools, field-immersed training and methods of performance validation. The outcome of the program was to result in better prepared and greater number of graduates ready to contribute to the field of power systems which depend upon the safe, reliable and efficient generation sources which make up an increasingly diverse mix of renewable power. Additionally, the program was to deliver critical training modules which are intended to support mid-career professionals and be woven into utility training programs used all over the country. Discontinuation Summary On September 29, 2014, Electricore received notice of discontinuation of federal funding under subject Award DE-EE0006339. DOE’s notice of discontinuation was the first indication provided to Electricore that the work completed against Task 1 - Program Planning and Evaluation during Budget Period 1 was inadequate. Significantly, the discontinuation was based in large part on the erroneous assertion that many of the tasks were incomplete as indicated in the Continuation Application. However, the Continuation Application was submitted July 29, 2014, while the period of performance for this last quarter in Budget Period 1 did not end until September 30, 2014. Accordingly, the performance for this last quarter in Budget Period 1 will be reported in the upcoming Quarterly Report which is not due until October 30, 2014. Nevertheless, in response to DOE’s letter and in further support of Electricore’s Continuation Application, we are providing a detailed status demonstrating adherence to all program requirements for each Task 1, Budget Period 1 SOPO activity and milestones in response to the DOE review.

14 SOLAR ENERGY↗

Final Evaluation Report for the Sandia National Laboratories Recorded Information Management Training Program

The Recorded Information Management (RIM) training and guidance materials were originally evaluated to determine the current status of the training program. Specifically, how and where are training materials implemented and are members of the workforce (MOWs) regularly accessing them. The evaluation highlighted that there is a breadth of training materials and guidance available; however, the materials are often outdated, point to old Sandia Policies, and/or are in outdated templates. Additionally, there is currently no single-entry point for training, meaning that training is available via the RIM homepage, TEDs, etc. This means that MOWs must search in various webpages or systems for training. To ensure RIM training materials are regularly updated and are accessible for MOWs it is recommended to assign one staff member to manage the program training materials.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Optimizing Distributed Training on Frontier for Large Language Models

Large language models (LLMs) have demonstrated remarkable success as foundational models, benefiting various downstream applications through fine-tuning. Loss scaling studies have demonstrated the superior performance of larger LLMs compared to their smaller counterparts. Nevertheless, training LLMs with billions of parameters poses significant challenges and requires considerable computational resources. For example, training a one trillion parameter GPT-style model on 20 trillion tokens requires a staggering 120 million exaflops. This research explores efficient distributed training strategies to extract this computation from Frontier, the world's first exascale supercomputer. We enable and investigate various model and data parallel training techniques, such as tensor parallelism, pipeline parallelism, and sharded data parallelism, to facilitate training a trillion-parameter model on Frontier. We empirically assess these techniques and their associated parameters to determine their impact on memory footprint, communication latency, and GPU's computational efficiency. We analyze the complex interplay among these techniques and find a strategy to combine them to achieve high throughput through hyperparameter tuning. We have identified efficient strategies for training large LLMs of varying sizes through empirical analysis and hyperparameter tuning. For 22 Billion, 175 Billion, and 1 Trillion parameters, we achieved GPU throughputs of 38.38%, 36.14%, and 31.96%, respectively. For the training of the 175 Billion parameter model and the 1 Trillion parameter model, we achieved 100% weak scaling efficiency on 1024 and 3072 Mi250X GPUs, respectively. We also achieved strong scaling efficiencies of 89% and 87% for these two models. We trained these models only tens of iterations instead of training till completion.

Yin, Junqi↗

Need for research and training reactors for advanced reactor designs

Full text of publication follows. Research and training reactors have served a valuable role in helping train workforce for currently operating fleet of light water reactors. These research and training reactors have been used in reactor laboratory classes to familiarize the students with such vital concepts as approach to criticality, reactor period, neutron moderation, reactivity, flux distribution and leakage, etc. As the industry moves toward advanced non-light-water reactor designs, it is critical that research and training reactors be developed and deployed at university campuses to help train the new generation of nuclear and non-nuclear engineers who are likely to design, build, and operate these advanced reactors. Among the designs currently being pursued for nuclear power generation include molten salt, sodium cooled, and gas cooled designs, with options for various fuel forms. Thus, industry and DOE in collaboration with academic institutions should devise plans on how to familiarize the next generation of nuclear workforce with hands-on experience necessary for such designs. These research and training reactors will play a vital role in familiarizing the future workforce with hands-on experience with concepts associated with fast spectrum reactors, gas cooled reactors, and other features not associated with light water reactors. In addition to classical nuclear engineering concepts, these advanced research and training reactors can also be used for hands-on training as well as for research on features being considered in the design of GEN-IV reactors: cyber security for digital control room operations, hybrid energy system, hydrogen generation, district heating, autonomous control... (author)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Endurance exercise training induces fat depot-specific differences in basal autophagic activity

The purpose of this study was to uncover the effect of exercise training on the expression of autophagy marker proteins in epididymal white adipose tissue (eWAT), inguinal WAT (iWAT), and the stromal vascular fraction (SVF) collected from eWAT. Male Wistar rats aged 4–5 weeks were randomly divided into two groups, sedentary control (n = 7) and exercise-trained (n = 7). Rats in the exercise-trained group were exercised on a treadmill set at a 5° incline 5 days/week for 9 weeks. We determined that the expression levels of an autophagosome-associating form of microtubule-associated protein 1 light chain 3 (LC3)-II and of p62 were significantly higher in eWAT from exercise-trained than from control rats, while those of adipose-specific deletion of autophagy-related protein (ATG7) and lysosomal-associated membrane protein type 2A (LAMP2a) showed no difference between groups. However, in iWAT, the expression levels of LC3-II and ATG7 were significantly higher in exercise-trained than in control rats. The expression of p62 was highly correlated with that of peroxisome proliferator-activated receptor γ (PPARγ), a master regulator of adipogenesis and lipid metabolism, in both WAT types (eWAT, r = 0.856, P < 0.05; iWAT, r = 0.762, P < 0.05), whereas LC3-II and PPARγ levels were highly correlated in eWAT (r = 0.765, P < 0.05) but not in iWAT (r = −0.306, ns). In SVF, the expression levels of LC3II, ATG7, and LAMP2a were significantly higher in exercise-trained than in control rats. These results suggest that exercise training suppresses basal autophagy activity in eWAT, but that this activity is enhanced in iWAT and SVF collected from eWAT. Thus, the adaptation of basal autophagic activity following exercise training exhibits fat depot-specific differences. - Highlights: • Autophagy has been associated with obesity and associated diseases. • We examined exercise-associated rat white adipose tissue (WAT) autophagy markers. • Exercise increased autophagosome associated LC3-II in WAT. • Exercise-induced changes in p62 and ATG7 were WAT-type specific. • Exercise-induced basal autophagic activity shows fat depot-specific differences.

60 APPLIED LIFE SCIENCES↗

PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy-Efficient ReRAM

The wide adoption of deep neural networks has been accompanied by ever-increasing energy and performance demands due to the expensive nature of training them. Additionally, numerous special-purpose architectures have been proposed to accelerate training: both digital and hybrid digital-analog using resistive RAM (ReRAM) crossbars. ReRAM-based accelerators have demonstrated the effectiveness of ReRAM crossbars at performing matrix-vector multiplication operations that are prevalent in training. However, they still suffer from inefficiency due to the use of serial reads and writes for performing the weight gradient and update step. A few works have demonstrated the possibility of performing outer products in crossbars, which can be used to realize the weight gradient and update step without the use of serial reads and writes. However, these works have been limited to low precision operations which are not sufficient for typical training workloads. Moreover, they have been confined to a limited set of training algorithms for fully-connected layers only. To address these limitations, we propose a bit-slicing technique for enhancing the precision of ReRAM-based outer products, which is substantially different from bit-slicing for matrix-vector multiplication only. We incorporate this technique into a crossbar architecture with three variants catered to different training algorithms. To evaluate our design on different types of layers in neural networks (fully-connected, convolutional, etc.) and training algorithms, we develop PANTHER, an ISA-programmable training accelerator with compiler support. Our design can also be integrated into other accelerators in the literature to enhance their efficiency. Our evaluation shows that PANTHER achieves up to 8.02×, 54.21×, and 103× energy reductions as well as 7.16×, 4.02×, and 16× execution time reductions compared to digital accelerators, ReRAM-based accelerators, and GPUs, respectively.

42 ENGINEERING↗

Large Scale Caching and Streaming of Training Data for Online Deep Learning

The training of deep neural network models on large data remains a difficult problem, despite progress towards scalable techniques. In particular, there is a mismatch between the random but predetermined order in which AI flows select training samples and the streaming I/O patterns for which traditional HPC data storage (e.g., parallel file systems) are designed. In addition, as more data are obtained, it is feasible neither simply to train learning models incrementally, due to catastrophic forgetting (i.e., bias towards new samples), nor to train frequently from scratch, due to prohibitive time and/or resource constraints. In this paper, we study data management techniques that combine caching and streaming with rehearsal support in order to enable efficient access to training samples in both offline training and continual learning. We revisit state-of-art streaming approaches based on data pipelines that transparently handle prefetching, caching, shuffling, and data augmentation, and discuss the challenges and opportunities that arise when combining these methods with data-parallel training techniques. We also report on preliminary experiments that evaluate the I/O overheads involved in accessing the training samples from a parallel file system (PFS) under several concurrency scenarios, highlighting the impact of the PFS on the design of the data pipelines.

data pipelines↗

Embedded training of neural-network subgrid-scale turbulence models

We report that the weights of a deep neural-network model are optimized in conjunction with the governing flow equations to provide a model for subgrid-scale stresses in a temporally developing plane turbulent jet at Reynolds number Re 0 = 6000 . The objective function for training is first based on the instantaneous filtered velocity fields from a corresponding direct numerical simulation, and the training is by a stochastic gradient descent method, which uses the adjoint Navier-Stokes equations to provide the end-to-end sensitivities of the model weights to the velocity fields. In-sample and out-of-sample testing on multiple dual-jet configurations show that its required mesh density in each coordinate direction for prediction of mean flow, Reynolds stresses, and spectra is half that needed by the dynamic Smagorinsky model for comparable accuracy. The same neural-network model trained directly to match filtered subgrid-scale stresses, without the constraint of being embedded within the flow equations during the training, fails to provide a qualitatively correct prediction. The coupled formulation is generalized to train based only on mean-flow and Reynolds stresses, which are more readily available in experiments. The mean-flow training provides a robust model, which is important, though a somewhat less accurate prediction for the same coarse meshes, as might be anticipated due to the reduced information available for training in this case. The anticipated advantage of the formulation is that the inclusion of resolved physics in the training increases its capacity to extrapolate. This is assessed for the case of passive scalar transport, for which it outperforms established models due to improved mixing predictions.

42 ENGINEERING↗

An Active Learning-Based Streaming Pipeline for Reduced Data Training of Structure Finding Models in Neutron Diffractometry

Structure determination workloads in neutron diffractometry are computationally expensive and routinely require several hours to many days to determine the structure of a material from its neutron diffraction patterns. The potential for machine learning models trained on simulated neutron scattering patterns to significantly speed up these tasks have been reported recently. However, the amount of simulated data needed to train these models grows exponentially with the number of structural parameters to be predicted and poses a significant computational challenge. To overcome this challenge, we introduce a novel batch-mode active learning (AL) policy that uses uncertainty sampling to simulate training data drawn from a probability distribution that prefers labelled examples about which the model is least certain. We confirm its efficacy in training the same models with ∼ 75% less training data while improving the accuracy. We then discuss the design of an efficient stream-based training workflow that uses this AL policy and present a performance study on two heterogeneous platforms to demonstrate that, compared with a conventional training workflow, the streaming workflow delivers ∼ 20% shorter training time without any loss of accuracy.

Wang, Tianle [Brookhaven National Laboratory (BNL)↗

Hindsight logging for model training

In modern Machine Learning, model training is an iterative, experimental process that can consume enormous computation resources and developer time. To aid in that process, experienced model developers log and visualize program variables during training runs. Exhaustive logging of all variables is infeasible, so developers are left to choose between slowing down training via extensive conservative logging, or letting training run fast via minimalist optimistic logging that may omit key information. As a compromise, optimistic logging can be accompanied by program checkpoints; this allows developers to add log statements post-hoc, and "replay" desired log statements from checkpoint---a process we refer to as hindsight logging. Unfortunately, hindsight logging raises tricky problems in data management and software engineering. Done poorly, hindsight logging can waste resources and generate technical debt embodied in multiple variants of training code. In this paper, we present methodologies for efficient and effective logging practices for model training, with a focus on techniques for hindsight logging. Our goal is for experienced model developers to learn and adopt these practices. To make this easier, we provide an open-source suite of tools for Fast Low-Overhead Recovery (flor) that embodies our design across three tasks: (i) efficient background logging in Python, (ii) adaptive periodic checkpointing, and (iii) an instrumentation library that codifies hindsight logging for efficient and automatic record-replay of model-training. Model developers can use each flor tool separately as they see fit, or they can use flor in hands-free mode, entrusting it to instrument their code end-to-end for efficient record-replay. Our solutions leverage techniques from physiological transaction logs and recovery in database systems. Evaluations on modern ML benchmarks demonstrate that flor can produce fast checkpointing with small user-specifiable overheads (e.g. 7%), and still provide hindsight log replay times orders of magnitude faster than restarting training from scratch.

Computer Science↗

Southwestern United States Carbon Sequestration Training Center

The Southwest CO 2 Training Center was initiated in November 2009 in response to the need to develop a generation of workers with expertise in carbon capture, utilization and storage (CCUS). Three universities ran the Training Center cooperatively: New Mexico Tech, the University of Utah and Texas A&M University. The overall approach of the Training Center was to conduct education and outreach at a wide range of educational levels, including K-12 students and teachers, undergraduate and graduate students, professionals, and the general public. Key activities included: (1) Outreach targeted development of a video game (Carbon Bond) for middle-school students. (2) A summer program for high-school students. (3) Training for K-12 educators in Utah with a program by the Keystone center on “the Climate Status” and two offerings of a Masters of Science Teaching class at New Mexico Tech (NMT) on Climate and Carbon Sequestration. (3) Development and approval of an undergraduate curriculum for a concentration in CCUS for geology majors offered at the Earth and Environmental Science Department at NMT. This included a new course in Carbon Sequestration Science and a field course in Reservoir and Caprock Geology. (4) A new graduate-level course in CCUS was developed and offered via distance education to students at the University of Utah (U of U), NMT and the University of Texas at El Paso (UTEP). (5) Professional training via a reservoir modeling class, opening up the university courses to professionals, and conducting three webinars on outreach and public perception in CCUS. Overall we offered 60 CEU credits and 2,598 hours of professional training. A business plan was developed to continue the Training Center's CCUS education into the future. This involves a collaborative agreement with Schlumberger Carbon Services using the expertise and on-line materials developed by the Training Center for a commercial professional development website.

Lee, Robert↗

Training and Certification Program for Certified Energy Auditors (CEA) and Certified Building Commissioning Professionals (CBCP)

The Association of Energy Engineers (AEE) has offered energy efficiency training and certification programs for over 30 years. During that time AEE has certified more than 22,000 professionals. All of our certification programs are the result of extensive industry research and program development and oversight by certification boards. For this project award, AEE proposed to work with the Department of Energy to utilize and extend existing industry recognized Certified Energy Auditor (CEA) and Certified Building Commissioning Professional (CBCP) programs under this Training Program Development Announcement. These expanded training programs will have significant impact in training professionals for building commissioning and energy auditing to achieve the goal of bringing existing buildings up to their optimal energy performance potential and ensuring that new buildings maintain their expected optimal level of performance. The goals and objectives of the training development project were achieved with the development of new training programs that are now being offered as self-sustaining commercial training and certification programs. These new programs are training and certifying professionals who are accomplishing the goal of increasing building energy performance in both existing and new buildings.

Kent, Bill↗

Enhanced Training for Cyber Situational Awareness in Red versus Blue Team Exercises

This report summarizes research conducted through the Sandia National Laboratories Enhanced Training for Cyber Situational Awareness in Red Versus Blue Team Exercises Laboratory Directed Research and Development project. The objective of this project was to advance scientific understanding concerning how to best structure training for cyber defenders. Two modes of training were considered. The baseline training condition (Tool-Based training) was based on current practices where classroom instruction focuses on the functions of a software tool with various exercises in which students apply those functions. In the second training condition (Narrative-Based training), classroom instruction addressed software functions, but in the context of adversary tactics and techniques. It was hypothesized that students receiving narrative-based training would gain a deeper conceptual understanding of the software tools and this would be reflected in better performance within a red versus blue team exercise.

97 MATHEMATICS AND COMPUTING↗