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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

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↗
DOE OSTI2020

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↗
DOE OSTI2022

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↗
NASA NTRS1991

Elevated central venous pressure: a consequence of exercise training-induced hypervolemia?

Resting blood volumes and arterial and central venous pressures (CVP) were measured in 14 men before and after exercise training to determine whether training-induced hypervolemia is accompanied by a change in total vascular capacitance. In addition, resting levels of plasma arginine vasopressin (AVP), atrial natriuretic peptide (ANP), aldosterone (Ald), and norepinephrine (NE) were measured. The same measurements were conducted in seven subjects who did not undergo exercise and acted as controls. Exercise training consisted of 10 wk of controlled cycle exercise for 30 min/day, 4 days/wk at 75-80% of maximal O2 uptake (VO2max). A training effect was verified by a 20% increase in VO2max, a resting bradycardia, and a 9% increase in blood volume. Mean arterial blood pressure was unaltered by exercise training, but resting CVP increased by 16% (P less than 0.05). The percent change in blood volume from before to after training was linearly related to the percent change in CVP (r = 0.903, P less than 0.05). As a consequence of elevations in both blood volume and CVP, the volume-to-pressure ratio was unchanged after exercise training. Plasma AVP, ANP, Ald, and NE were unaltered. Our results indicate that elevated CVP is a consequence of training-induced hypervolemia without alteration in total effective venous capacitance.

NASA Program Space Physiology and Countermeasures↗
NASA NTRS2007

Revisiting Training and Verification Process Implementation for Risk Reduction on New Missions at NASA Jet Propulsion Laboratory

In 2003 we proposed an effort to develop a core program of standardized training and verification practices and standards against which the implementation of these practices could be measured. The purpose was to provide another means of risk reduction for deep space missions to preclude the likelihood of a repeat of the tragedies of the 1998 Mars missions. We identified six areas where the application of standards and standardization would benefit the overall readiness process for flight projects at JPL. These are Individual Training, Team Training, Interface and Procedure Development, Personnel Certification, Interface and procedure Verification, and Operations Readiness Testing. In this paper we will discuss the progress that has been made in the tasks of developing the proposed infrastructure in each of these areas. Specifically we will address the Position Training and Certification Standards that are now available for each operational position found on our Flight Operations Teams (FOT). We will also discuss the MGSS Baseline Flight Operations Team Training Plan which can be tailored for each new flight project at JPL. As these tasks have been progressing, the climate and emphasis for Training and for V and V at JPL has changed, and we have learned about the expansion, growth, and limitations in the roles of traditional positions at JPL such as the Project's Training Engineer, V and V Engineer, and Operations Engineer. The need to keep a tight rein on budgets has led to a merging and/or reduction in these positions which pose challenges to individual capacities and capabilities. We examine the evolution of these processes and the roles involved while taking a look at the impact or potential impact of our proposed training related infrastructure tasks. As we conclude our examination of the changes taking place for new flight projects, we see that the importance of proceeding with our proposed tasks and adapting them to the changing climate remains an important element in reducing the risk in the challenging business of space exploration.

verifications↗
NASA NTRS2014

Identification of Medical Training Methods for Exploration Missions

As the National Aeronautics and Space Administration (NASA) and its international partner agencies anticipate eventual exploration missions of longer duration, there is a need to plan for the medical capabilities necessary to maximize crew health and provide the best likelihood of mission success. Current spaceflights consist of 5- to 6-month excursions to the International Space Station (ISS) in low-Earth orbit (LEO), and a 12-month ISS mission is currently in planning stages. However, missions to a near-Earth asteroid (NEA), a return to the moon, or even a mission to Mars will demand unprecedented medical capabilities, particularly relating to the training of the crew medical officers (CMOs). In its attempts to address the questions about medical preparation for spaceflight beyond LEO, the Exploration Medical Capability (ExMC) element within NASA's Human Research Program (HRP) defines a series of gaps. These gaps are shortcomings in knowledge, training, or technology that require resolution before an exploration mission can be undertaken. The ExMC element maintains current information about measures to close these gaps while developing plans for further investigation and research. Data pertaining to the gaps and their present status are available to the general public on the NASA Human Research Wiki and the NASA Human Research Roadmap Web sites (34, 36). One such gap, Gap 3.01, identifies a lack of knowledge about the optimal training methods for in-flight medical conditions identified on the Exploration Medical Condition List (EMCL), taking into account the crew medical officer s (CMOs) clinical background (33). This broad statement encompasses several related issues with the current methods of training CMOs and the medical ground support staff, specifically flight surgeons and biomedical engineers (BMEs) located in mission control, in addition to questions pertaining to the ways in which training will need to be adapted for the medical contingencies unique to exploration missions. To determine the optimal methods of medical training for an exploration medical crew and their ground support team, the historical context of medical operations, the current CMO training methods, and potential alternative training methods were identified.

Long duration space flight↗
NASA NTRS2015

Effects of False Tilt Cues on the Training of Manual Roll Control Skills

This paper describes a transfer-of-training study performed in the NASA Ames Vertica lMotion Simulator. The purpose of the study was to investigate the effect of false tilt cues on training and transfer of training of manual roll control skills. Of specific interest were the skills needed to control unstable roll dynamics of a mid-size transport aircraft close to the stall point. Nineteen general aviation pilots trained on a roll control task with one of three motion conditions: no motion, roll motion only, or reduced coordinated roll motion. All pilots transferred to full coordinated roll motion in the transfer session. A novel multimodal pilot model identification technique was successfully applied to characterize how pilots' use of visual and motion cues changed over the course of training and after transfer. Pilots who trained with uncoordinated roll motion had significantly higher performance during training and after transfer, even though they experienced the false tilt cues. Furthermore, pilot control behavior significantly changed during the two sessions, as indicated by increasing visual and motion gains, and decreasing lead time constants. Pilots training without motion showed higher learning rates after transfer to the full coordinated roll motion case.

simulators↗
NASA NTRSDate not supplied

ISS Payload Operations Training During the COVID-19 Pandemic: Impacts and Solutions

The onset of the COVID-19 pandemic brought a dramatic and rapid transformation to almost every aspect of humanity in 2020. The world’s space agencies and their missions were not immune to the wide-sweeping changes. One discipline principally affected was mission operations and the various groups supporting that function. Mission support teams, especially for complex and crewed missions like the International Space Station were forced to rapidly rethink how and where control center staff performed their vital work. Operations training – an essential element to mission ops, had unique hurdles to overcome. Operations training is responsible for preparing astronaut crews for their missions, providing training to flight controllers, as well as ensuring that new team members are ready to join their colleagues. Every element of training was impacted by COVID restrictions. From orientation and introductory classes for new controllers, simulations and advanced lessons, On the Job Training and final evaluations; all aspects faced new challenges. Trainers at NASA’s Marshall Space Flight Center in Huntsville, Alabama, were forced to become more efficient with trainees and resources to continue supporting payload operations. The pandemic started in the USA in March 2020. Immediately, NASA mandated that the support for ISS real-time operations was critical. As a result, physical access to key facilities was restricted. Trainers and trainees had to quickly shift to 100 percent remote learning. In the short term, this was not a problem. However, instructors discovered lessons that they were accustomed to delivering in a classroom environment did not translate to remote teaching. Another hurdle to operations training was the mandate that all simulations could only be held remotely. The logistics of even small simulations proved to be challenging due to IT restrictions and public internet limitations. With simulations essentially stopped, as well as the restrictions on most OJT, trainees were essentially stopped in their advancement towards certification. Once limitations were identified, trainers prioritized new options. Transitioning to all electronic learning materials was a relatively easy fix. Teaching to large groups took additional shifts in the training paradigm. Methods for preparing astronauts for their missions were revised. Simulation supervisors found more efficient techniques to provide realistic training experience. Communication and approvals from management was essential. In every case, the payload operations instructors found novel solutions to all functions listed. This paper will discuss the factors and solutions payloads operations trainers found to keep scientific research on the ISS flying forward to mission success.

ISS↗
NASA NTRS2022

ISS Payload Operations Training Throughout the COVID-19 Pandemic: Impacts, Opportunities and Solutions

The onset of the COVID-19 pandemic brought a dramatic and rapid transformation to almost every aspect of humanity. The world’s space agencies and their missions were not immune to the wide-sweeping changes. One discipline principally affected was mission operations and the various groups supporting that function. Mission support teams, especially for complex and crewed missions like the International Space Station (ISS) were forced to rethink how and where control center staff performed their vital work. Operations training – an essential element to mission ops, had unique hurdles to overcome. Operations training is responsible for preparing astronaut crews for their missions, training and certifying flight controllers, as well as ensuring that new team members are ready to join their colleagues. Every element of training was impacted during the pandemic. From orientation and introductory classes for new controllers, simulations, and advanced lessons, On the Job Training (OJT) and final evaluations; all aspects faced challenges. Trainers at NASA’s Marshall Space Flight Center in Huntsville, Alabama were forced to become more efficient with trainees and resources to continue supporting ISS payload operations. The pandemic arrived in the USA in March 2020. Immediately, NASA mandated that the support for ISS real-time operations was critical. As a result, physical access to key facilities was restricted. Trainers and trainees had to quickly shift to 100% remote learning. In the short term, this was not a problem. However, instructors discovered lessons they were accustomed to delivering in a classroom environment often did not translate to remote teaching. Another hurdle to operations training was the mandate that all simulations could only be held remotely. The logistics of even small simulations proved to be challenging due to Information Technology (IT) restrictions and public internet limitations. With simulations essentially halted, as well as the restrictions on most OJT, trainees were essentially stopped in their advancement towards certification. Once limitations were identified, trainers prioritized new options. Transitioning to all electronic learning materials was a relatively easy fix. Teaching to large groups took additional shifts in the training paradigm. Methods for preparing astronauts for their missions were revised. Simulation supervisors found efficient techniques to provide realistic training experiences. Communication and coordination with management was essential. In every case, the payload operations instructors found novel solutions to all functions listed. This paper discusses the factors and solutions payloads operations trainers found to keep scientific research on the ISS flying forward to mission success.

ISS↗
NASA NTRSDate not supplied

Lessons Learned in the Implementation of a Training Knowledge Management System for the SERVIR Network

The SERVIR program is a unique partnership between NASA, the U.S. Agency for International Development (USAID), focusing on building capacity to use Earth observations for addressing development challenges. In that context, between 2004 and 2020, the program delivered approximately 365 trainings to almost 10,000 professionals. More recently, between November 2020 and August 2021, the SERVIR network executed some 55 training events addressing SERVIR’s 4 priority thematic areas, and roughly a quarter of SERVIR trainings overall have focused on themes related to Ecological Forecasting. Due to the ongoing COVID-19 pandemic, almost four-fifths of recent training events have been virtual, with the remainder being in-person under limited circumstances. The large number of training events delivered represents both an opportunity and a challenge in terms of knowledge management. While the training materials developed can later be reused in other parts of the SERVIR network, prior to recently, the lack of a central repository for those materials has prevented wider dissemination and use. The recently developed Training Knowledge Management System (TKMS) is now becoming an integral part of the SERVIR Capacity Building Framework, supporting the exchange of resources and methods for conducting training activities across the network. This presentation focuses on the structure of this system, as well as on the anticipated benefits for the User Communities for Earth Observations of Terrestrial Systems.

training↗
NASA NTRSDate not supplied

Preparing for Lunar Exploration: Geology and Field Training for Astronauts

NASA astronauts will soon return to the Moon, this time to the lunar south pole. Astronauts will perform traverses, make geologic observations, and collect samples to return to Earth. Lessons from Apollo show that science returns were optimized because crews were well-trained in both spacewalk operations and field geology. In that spirit, our team of geologists introduced a revised geologic training program for in-coming NASA astronauts that includes classroom activities and fieldwork and is split over 2 years. Year 1 focuses on an introduction to geologic concepts capped by a field exercise. Year two focuses on climate change, the Moon, other planets, and additional fieldwork. Our geology curriculum supports astronaut observations from the ISS and is the foundation for future Artemis geology training, which will include lunar science and increasingly complex field training in planetary-relevant locations. A final piece of our training program provides geology and field mapping experiences for NASA engineers, flight controllers, and managers, to help them understand the principles of fieldwork and relevance to lunar exploration. The Year 1 geology training must be an effective introduction for astronauts who have little or no background in geology. We focus the training around a narrowly defined field problem and use a week of classroom training to prepare the astronauts with the specific skills and background they need to carry out a field exercise on volcanic features, structures, and landforms of the Taos Plateau, New Mexico. Classroom modules are hands-on, using satellite imagery, maps, analog models, and samples, and provide the astronauts with specific and relevant experience in how to make observations and describe what they see, recognize, and interpret patterns, infer processes from products, and analyze relationships to build a story based on evidence from a variety of data sources. At the end of each classroom day, astronauts work in teams to build a preliminary geologic map of the field area, adding new observations and interpretations as they learn about topics in the classroom. Each team’s bucket list of target areas to visit helps shape their investigations during their week in the field. On the final day in the field, each astronaut team presents a geologic map, cross section, and geologic interpretation

Geology↗
DOE OSTI2021

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↗
DOE OSTI2024

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)↗
DOE OSTI2020

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↗
DOE OSTI2018

Summary of Observations from the 2017 Federal Radiological Monitoring and Assessment Center (FRMAC) Laboratory Analysis Training and Capstone Event

On August 15th thru 17th, 2017 the Federal Radiological Monitoring and Assessment Center (FRMAC) Laboratory Analysis division, the FRMAC Fly Away Laboratory (FAL), the FRMAC Assessment division, and the Mobile Environmental Response Laboratory (MERL) held a training and capstone event for staff from the Environmental Protection Agency (EPA), Remote Sensing Laboratory (RSL), Lawrence Livermore National Laboratory (LLNL), and Sandia National Laboratories (SNL). LAB-100, "Sample Control Training", LAB-200 "QA Specialist Training", and LAB-300 "Laboratory Analysis Manager Training" was given the first two days of the event. The purpose of the training and capstone event was to meet training requirements for billeted FRMAC Lab Analysis staff from RSL, LLNL, and SNL as well as raise awareness of the FRMAC Lab Analysis process with EPA staff as part of a Federal Emergency Management Agency — Nuclear Incident Response Team (FEMA-NIRT) laboratory standardization project. An objective of the standardization project was to help improve the transition of operations from DOE to EPA during a response. To do this effectively, detailed knowledge of the FRMAC Lab Analysis process by the EPA is needed. This training provided a good opportunity for this knowledge transfer. A capstone was held after the two-day training event to allow participants to practice the skills they learned in a realistic scenario. A scenario that was previously developed for a quarterly Consequence Management drill (i.e. Dark Phoenix) was used as the basis for the capstone, with laboratory analysis focused injects used to drive the exercise play. Each position within the FRMAC Lab Analysis Division exercised to specific objectives and helped to uncover gaps in the established processes. The lessons learned during this capstone are broken out in the following categories: Sample Control, In-Situ Gamma Spectroscopy, Analysis Request Forms (ARF), Shipping, QA/QC, Fly Away Laboratory (FAL), and Management.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2018

The Michigan New Technology Training and Research (MNTR) Translational Program in Nuclear Medicine (Final Report)

The Michigan New Technology Training and Research (MNTR) Translational Program in Nuclear Medicine and Molecular Imaging This project established the Michigan New Technology Training and Research (MNTR) translational program, focused on the acceleration of new clinical molecular imaging methods. Molecular imaging approaches to imaging are a very flexible and powerful development, with many recent examples advancing the diagnosis and guiding the management of human disease. These methods depend on the design, synthesis and testing of new radiotracers (molecules designed to target specific cells or tissues in the body), labeled with short-lived radioactive atoms (positron emitters). The new radiotracers are imaged in the human body using positron emission tomography (PET) imaging. The University of Michigan PET Center has considerable experience in the discovery, development, refinement and initial human applications of new PET radiotracers. An emerging impediment to efficient availability of new PET radiotracers, however, involves the regulatory environment at multiple levels. Many potentially successful ideas are delayed or even prevented from entering human use by these barriers. In the current grant, we provided hands-on experience for the next generation of young scientists working in molecular imaging so that they are equipped to effectively move new ideas and radiotracers from the research laboratory to the nuclear medicine clinic (bench-to-bedside). For new radiotracer development, oversight by the Food and Drug Administration (FDA), the Nuclear Regulatory Commission (NRC), and local institutional committees and reviews are required. These aspects of translation from laboratory to clinic are often omitted from the formal training of new scientists, but were provided to three trainees via direct mentorship in the MNTR program. The MNTR training program built on the translational successes of the University of Michigan Division of Nuclear Medicine and capitalized on our strengths (facilities, faculty, a wide-ranging selection of projects, and the experience and commitment to bring new radiotracers into human studies) to systematically train three fellows in radiochemistry and nuclear medicine. Integrated training in development, validation and clinical translation of new PET radiotracers occurred through practical involvement in multiple research projects, each at a different stage along the pathway from bench-to-bedside. Each trainee obtained experience of the entire process over about 2 years. Projects involved development of new radiotracers for neurodegenerative disorders (e.g. Alzheimer disease), movement disorders (e.g. Parkinson disease, progressive supranuclear palsy) and neurodevelopmental syndromes (e.g. Tourette syndrome) as well as new radiochemistry methods for synthesizing radiotracers. Each project was pursued in a close collaboration between the fellow trainee and both the clinical and basic science faculty at the University of Michigan PET Center, and provided an unprecedented opportunity for the highest-level training in academic radiochemistry and nuclear medicine research. The project has resulted in 17 peer-reviewed publications to date, and at least 4 more are in preparation. Additionally, 1 book chapter and 26 conference presentations have resulted from this grant. Upon completion of the MNTR Program, the trainees have emerged as translational scientists wielding the necessary skill-set (practical research experience, multidisciplinary training, regulatory know-how) to embark on successful careers in translational molecular imaging, bringing continued advances in the field to bear on important human disorders. As a metric of the Program’s success, one fellow has already secured employment in the field, while the other two are finishing writing papers; they wish to also stay in the radiochemistry and nuclear medicine community, and are currently applying for jobs.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2021

Training Restricted Boltzmann Machines With a D-Wave Quantum Annealer

Restricted Boltzmann Machine (RBM) is an energy-based, undirected graphical model. It is commonly used for unsupervised and supervised machine learning. Typically, RBM is trained using contrastive divergence (CD). However, training with CD is slow and does not estimate the exact gradient of the log-likelihood cost function. In this work, the model expectation of gradient learning for RBM has been calculated using a quantum annealer (D-Wave 2000Q), where obtaining samples is faster than Markov chain Monte Carlo (MCMC) used in CD. Training and classification results of RBM trained using quantum annealing are compared with the CD-based method. The performance of the two approaches is compared with respect to the classification accuracies, image reconstruction, and log-likelihood results. The classification accuracy results indicate comparable performances of the two methods. Image reconstruction and log-likelihood results show improved performance of the CD-based method. It is shown that the samples obtained from quantum annealer can be used to train an RBM on a 64-bit “bars and stripes” dataset with classification performance similar to an RBM trained with CD. Though training based on CD showed improved learning performance, training using a quantum annealer could be useful as it eliminates computationally expensive MCMC steps of CD.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Reliable Determination of Pulses and Pulse-Shape Instability in Ultrashort Laser Pulse Trains Using Polarization-Gating and Transient-Grating Frequency-Resolved Optical Gating Using the RANA Approach

Devices that measure the presence of instability in the pulse shapes in trains of ultrashort laser pulses do not exist, so this task necessarily falls to pulse-measurement devices, like Frequency-Resolved Optical Gating (FROG) and its variations, which have proven to be a highly reliable class of techniques for measuring stable trains of ultrashort laser pulses. Fortunately, multi-shot versions of FROG have also been shown to sensitively distinguish trains of stable from those of unstable pulse shapes by displaying readily visible systematic discrepancies between the measured and retrieved traces in the presence of unstable pulse trains. However, the effects of pulse-shape instability and algorithm stagnation can be indistinguishable, so a never-stagnating algorithm—even when instability is present—is required and is generally important. In previous work, we demonstrated that our recently introduced Retrieved-Amplitude N-grid Algorithmic (RANA) approach produces highly reliable (100%) pulse-retrieval in the second-harmonic-generation (SHG) version of FROG for thousands of sample trains of pulses with stable pulse shapes. Further, it does so even for trains of unstable pulse shapes and thus both reliably distinguishes between the two cases and provides a rough measure of the degree of instability as well as a reasonable estimate of most typical pulse parameters. Here, we perform the analogous study for the polarization-gating (PG) and transient-grating (TG) versions of FROG, which are often used for higher-energy pulse trains. We conclude that PG and TG FROG, coupled with the RANA approach, also provide reliable indicators of pulse-shape instability. In addition, for PG and TG FROG, the RANA approach provides an even better estimate of a typical pulse in an unstable pulse train than SHG FROG does, even in cases of significant pulse-shape instability.

47 OTHER INSTRUMENTATION↗