Interocular transfer in goldfish - color easier than pattern.
Monocular discrimination by trained goldfish of different patterns and colors, showing interhemispheric color information transfer more effective than pattern
ANIMAL STUDY↗
SEARCH · Search NASA
Results for “TRANSFER OF TRAINING”
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.
Enriching the Twitter Stream Increasing Data Mining Yield and Quality Using Machine Learning
Social media data streams are important sources of real-time and historical global information for science applications. At the NASA Goddard Earth Sciences Data and Information Services Center (GES DISC), we are exploring the Twitter data stream for its potential in augmenting the validation program of NASA Earth science missions, specifically the Global Precipitation Measurement (GPM) mission. We have implemented a tweet processing infrastructure that outputs classified precipitation tweets. Inputs are "passive" tweets, along with a smaller number of tweets from "active" participants, i.e., those knowingly contributing to our effort. The "active" tweets, presumably of higher quality, enrich the Twitter stream. "Active" sources include data scraped from other social media (e.g., public Facebook posts) and data from existing crowdsourcing programs (e.g., mPING reports). In addition, there is likely relevant precipitation information in images and documents that are the end points of links often included in tweets. Information derived from these "active" sources could then be tweeted into the Twitter stream, thus enriching its quality. The objective of our current work is to mine these tweet linked images and documents, using neural networks, to increase the information content and quality related to precipitation. For images, we classified them as either precipitation-related or not. For training and validation, we used images obtained via the Google custom search API. We created two models: (1) by training a simple Convolutional Neural Network and (2) by using transfer learning principles to adapt a pre-trained object recognition model. For documents, both those linked to tweets and the tweet contents, we trained Hierarchical Attention Networks to determine precipitation occurrence, type, and intensity. For training and validation, we used a keyword-filtered tweet data set labelled with ground truth data from Dark Sky (an API to retrieve weather-related labels) and the National Severe Storms Laboratory's Multi Radar/Multi-Sensor (MRMS) system. Our results demonstrated the efficacy of our machine learning approaches for enriching the Twitter stream, to derive information potentially useful for validation of earth science satellite data.
Albayrak, Arif↗
Exploring the Low-Thrust Transfer Design Space in an Ephemeris Model via Multi-Objective Reinforcement Learning
Multi-Reward Proximal Policy Optimization (MRPPO) is a multi-objective reinforcement learning algorithm used to train multiple policies to uncover solutions within a multi-objective solution space. MRPPO is used in this paper to train policies to construct low-thrust transfers for a SmallSat from the vicinity of !2 to an !5 short period orbit in the Sun-Earth-Moon system. First, the policies are trained in this scenario in the circular restricted three-body problem. This information is used to initialize the policies before training in a higher-fidelity ephemeris model; a process known as transfer learning. The recovered segments of the solution space will be compared to fundamental dynamical structures to both examine the results of MRPPO in this complex design scenario and explore the effectiveness of transfer learning.
Christopher J Sullivan↗
Exploring the Low-Thrust Transfer Design Space in an Ephemeris Model via Multi-Objective Reinforcement Learning
Multi-Reward Proximal Policy Optimization (MRPPO) is a multi-objective reinforcement learning algorithm used to train multiple policies to uncover solutions within a multi-objective solution space. MRPPO is used in this paper to train policies to construct low-thrust transfers for a SmallSat from the vicinity of L2 to an L5 short period orbit in the Sun-Earth-Moon system. First, the policies are trained in this scenario in the circular restricted three-body problem. This information is used to initialize the policies before training in a higher-fidelity ephemeris model; a process known as transfer learning. The recovered segments of the solution space will be compared to fundamental dynamical structures to both examine the results of MRPPO in this complex design scenario and explore the effectiveness of transfer learning.
Christopher J. Sullivan↗
Exploring the Low-Thrust Transfer Design Space in an Ephemeris Model via Multi-Objective Reinforcement Learning
Multi-Reward Proximal Policy Optimization (MRPPO) is a multi-objective reinforcement learning algorithm used to train multiple policies to uncover solutions within a multi-objective solution space. MRPPO is used in this paper to train policies to construct low-thrust transfers for a SmallSat from the vicinity of 𝐿2 to an 𝐿5 short period orbit in the Sun-Earth-Moon system. First, the policies are trained in this scenario in the circular restricted three-body problem. This information is used to initialize the policies before training in a higher-fidelity ephemeris model; a process known as transfer learning. The recovered segments of the solution space will be compared to fundamental dynamical structures to both examine the results of MRPPO in this complex design scenario and explore the effectiveness of transfer learning.
Mashiku, Alinda K.↗
Generalizability of Manual Control Skills Between Control Tasks of Varying Difficulty
This paper presents the results of an experiment that was performed at NASA Ames Research Center using 18 participants in two different groups who trained a task for ten days, with the goal of identifying how skill generalization would occur between two similar tasks of varying difficulty. A cybernetic approach was used. The first group was trained in a simple one-dimensional tracking task and transferred to a difficult two-dimensional tracking task. For the second group, this was reversed. Training with a simple task before transferring to the difficult task resulted in a slower convergence to final performance. However, it did allow participants to start with a better initial performance in the difficult task. Furthermore, after training with a simple task, participants controlled with a higher gain and generated lower lead time constants. However, possibly due to the number of participants, this experiment did not find any statistical evidence to support the conclusion that training with a simple task version helps in learning a more complex task.
skill generalizability↗
Generalizability of Manual Control Skills between Control Tasks of Varying Difficulty
This paper presents the results of an experiment that was performed at NASA Ames Research Center using 18 participants in two different groups who trained a task for ten days, with the goal of identifying how skill generalization would occur between two similar tasks of varying difficulty. A cybernetic approach was used. The first group was trained in a simple one-dimensional tracking task and transferred to a difficult two-dimensional tracking task. For the second group, this was reversed. Training with a simple task before transferring to the difficult task resulted in a slower convergence to final performance. However, it did allow participants to start with a better initial performance in the difficult task. Furthermore, after training with a simple task, participants controlled with a higher gain and generated lower lead time constants. However, possibly due to the number of participants, this experiment did not find any statistical evidence to support the conclusion that training with a simple task version helps in learning a more complex task.
Pieters, Marc A.↗
Neural Network and Response Surface Methodology for Rocket Engine Component Optimization
The goal of this work is to compare the performance of response surface methodology (RSM) and two types of neural networks (NN) to aid preliminary design of two rocket engine components. A data set of 45 training points and 20 test points obtained from a semi-empirical model based on three design variables is used for a shear coaxial injector element. Data for supersonic turbine design is based on six design variables, 76 training, data and 18 test data obtained from simplified aerodynamic analysis. Several RS and NN are first constructed using the training data. The test data are then employed to select the best RS or NN. Quadratic and cubic response surfaces. radial basis neural network (RBNN) and back-propagation neural network (BPNN) are compared. Two-layered RBNN are generated using two different training algorithms, namely solverbe and solverb. A two layered BPNN is generated with Tan-Sigmoid transfer function. Various issues related to the training of the neural networks are addressed including number of neurons, error goals, spread constants and the accuracy of different models in representing the design space. A search for the optimum design is carried out using a standard gradient-based optimization algorithm over the response surfaces represented by the polynomials and trained neural networks. Usually a cubic polynominal performs better than the quadratic polynomial but exceptions have been noticed. Among the NN choices, the RBNN designed using solverb yields more consistent performance for both engine components considered. The training of RBNN is easier as it requires linear regression. This coupled with the consistency in performance promise the possibility of it being used as an optimization strategy for engineering design problems.
Vaidyanathan, Rajkumar↗
Development of user applications for earth resources survey data in urban and regional planning in the Puget Sound area
User applications of remote sensing in Washington State are described. The first project created a multi-temporal land use/land cover data base for the environs of the Seattle-Tacoma International Airport, to serve planning and management operations of the Port of Seattle. The second is an on-going effort to develop a capability within the Puget Sound Governmental Conference, a council of governments (COG), to inventory and monitor land use within its four county jurisdiction. Developmental work has focused on refinement of land use/cover classification systems applicable at this regional scale and various levels of detail in relation to program requirements of the agency. Related research, refinement of manual methods, user training and approaches to technology transfer are discussed.
Westerlund, F. V.↗
Advantages of Measuring the Q Stokes Parameter in Addition to the Total Radiance I in the Detection of Absorbing Aerosols: a Proof of Concept Using Vector Radiative Transfer, Neural Networks, and Optimal Estimation
A simple but novel study was conducted to investigate whether an imager-type spectroradiometer instrument like MODIS, currently flying on board the Aqua and Terra satellites, or MERIS, which flew on board Envisat, could detect absorbing aerosols if they could measure the Q Stokes parameter in addition to the total radiance I, that is if they could also measure the linear polarization of the light. Accurate radiative transfer calculations were used to train a fast neural network forward model, which together with a simple statistical optimal estimation scheme was used to retrieve three aerosol parameters: aerosol optical depth, fraction of absorbing aerosols, and aerosol location. The aerosols were assumed to be located either between 0 and 2 km or between 2 and 4 km in the Earth’s atmosphere. From simulated data it was found that by itself the total radiance I was generally insufficient to retrieve all three aerosol parameters, but that together with the Q Stokes component it was possible to reliably retrieve values of aerosol optical depth, fraction, and location.
Stamnes, Snorre↗
NASA-Navy Telemedicine: Autogenic Feedback Training Exercises for Motion Sickness
Airsickness is the most significant medical condition affecting naval aviation training. A 2001 study showed that airsickness was reported in 81% of naval aviation students and was associated with 82% of below average flight scores. The cost to a single training air-wing was over $150,000 annually for fuel and maintenance costs alone. Resistent cases are sent to the Naval Aerospace Medical Institute (NAMI) for evaluation and desensitization in the self-paced airsickness desensitization (SPAD) program. This approach is 75% successful, but can take up to 8 weeks at a significant travel cost. NASA Ames Research Center's Autogenic Feedback Training Exercises (AFTE) uses physiological and biofeedback training for motion sickness prevention. It has a remote capability that has been used from Moffett Field, CA to Atlanta, GA . AFTE is administered in twelve (30-minute) training sessions. The success rate for the NASA AFTE program has been over 85%. Methods: Implementation Phases: Phase I: Transfer NASA AFTE to NAMI; NASA will remotely train aviation students at NAMI. Phase II: NAMI-centered AFTE application with NASA oversight. Phase III: NAMI-centered AFTE to remotely train at various Navy sites. Phase IV: NAMI to offer Tri-service application and examine research opportunities. Results: 1. Use available telemedicine connectivity between NAMI and NASA. 2. Save over $2,000 per student trained. 3. Reduce aviation training attrition. 4. Provide standardization of multi-location motion sickness training. 5. Future tri-service initiatives. 6. Data to NASA and Navy for QA and research opportunities.
Acromite, Michael T.↗
Training state agency personnel in satellite remote sensing technology - Solutions to a special problem
To aid state/local agencies in starting effective programs to apply Landsat and other remote sensing data, NASA's Eastern Regional Remote Sensing Applications Center (ERRSAC) has developed a comprehensive training program as part of its technology transfer mission. Skills in data processing and interpretation are produced through 'hands-on' experience with computer techniques used to conduct practical applications involving state-oriented projects, conducted jointly by agencies and ERRSAC. In time, ERRSAC will shift much of these training activities to universities where future agency personnel can obtain a broader foundation in remote sensing.
Short, N. M.↗
Microstructure Segmentation With Deep Learning Encoders Pre-Trained on a Large Microscopy Dataset
This study examined the improvement of microscopy segmentation intersection over union accuracy by transfer learning from a large dataset of microscopy images called MicroNet. Many neural network encoder architectures were trained on over 100,000 labeled microscopy images from 54 material classes. These pre-trained encoders were then embedded into multiple segmentation architectures including UNet and DeepLabV3+ to evaluate segmentation performance on created benchmark microscopy datasets. Compared to ImageNet pre-training, models pre-trained on MicroNet generalized better to out-of-distribution micrographs taken under different imaging and sample conditions and were more accurate with less training data. When training with only a single Ni-superalloy image, pre-training on MicroNet produced a 72.2% reduction in relative intersection over union error. These results suggest that transfer learning from large in-domain datasets generate models with learned feature representations that are more useful for downstream tasks and will likely improve any microscopy image analysis technique that can leverage pre-trained encoders.
machine learning↗
Experimental Evaluation of a Structure-Based Connectionist Network for Fault Diagnosis of Helicopter Gearboxes
This paper presents the experimental evaluation of the Structure-Based Connectionist Network (SBCN) fault diagnostic system introduced in the preceding article. For this vibration data from two different helicopter gearboxes: OH-58A and S-61, are used. A salient feature of SBCN is its reliance on the knowledge of the gearbox structure and the type of features obtained from processed vibration signals as a substitute to training. To formulate this knowledge, approximate vibration transfer models are developed for the two gearboxes and utilized to derive the connection weights representing the influence of component faults on vibration features. The validity of the structural influences is evaluated by comparing them with those obtained from experimental RMS values. These influences are also evaluated ba comparing them with the weights of a connectionist network trained though supervised learning. The results indicate general agreement between the modeled and experimentally obtained influences. The vibration data from the two gearboxes are also used to evaluate the performance of SBCN in fault diagnosis. The diagnostic results indicate that the SBCN is effective in directing the presence of faults and isolating them within gearbox subsystems based on structural influences, but its performance is not as good in isolating faulty components, mainly due to lack of appropriate vibration features.
Jammu, V. B.↗
Microstructure Segmentation with Deep Learning Encoders Pre-Trained on a Large Microscopy Dataset
This study examined the improvement of microscopy segmentation accuracy by transfer learning from a large dataset of microscopy images called MicroNet. Many neural network encoder architectures, including VGG, Inception, and ResNet, were trained on over 100,000 labelled microscopy images from 54 classes. These pre-trained encoders were then embedded into multiple segmentation architectures including U-Net and DeepLabV3+ to evaluate segmentation performance on newly created benchmark microscopy datasets. Compared to ImageNet pre-training, models pre-trained on MicroNet generalized better to out-of-distribution micrographs taken under different imaging and sample conditions and were more accurate with less training data. When training with only a single Ni-superalloy image, pre-training on MicroNet produced a 72.2 percent reduction in relative segmentation error. These results suggest that transfer learning from large in-domain datasets generate models with learned feature representations that are more useful for downstream tasks and will likely improve any microscopy image analysis technique that can leverage pre-trained encoders.
machine learning↗
Mentoring SFRM: A New Approach to International Space Station Flight Controller Training
The Mission Operations Directorate (MOD) of the Johnson Space Center is responsible for providing continuous operations support for the International Space Station (ISS). Operations support requires flight controllers who are skilled in team performance as well as the technical operations of the ISS. Space Flight Resource Management (SFRM), a NASA adapted variant of Crew Resource Management (CRM), is the competency model used in the MOD. ISS flight controller certification has evolved to include a balanced focus on development of SFRM and technical expertise. The latest challenge the MOD faces is how to certify an ISS flight controller (operator) to a basic level of effectiveness in 1 year. SFRM training uses a two-pronged approach to expediting operator certification: 1) imbed SFRM skills training into all operator technical training and 2) use senior flight controllers as mentors. This paper focuses on how the MOD uses senior flight controllers as mentors to train SFRM skills. Methods: A mentor works with an operator throughout the training flow. Inserted into the training flow are guided-discussion sessions and on-the-job observation opportunities focusing on specific SFRM skills, including: situational leadership, conflict management, stress management, cross-cultural awareness, self care and team care while on-console, communication, workload management, and situation awareness. The mentor and operator discuss the science and art behind the skills, cultural effects on skills applications, recognition of good and bad skills applications, recognition of how skills application changes subtly in different situations, and individual goals and techniques for improving skills. Discussion: This mentoring program provides an additional means of transferring SFRM knowledge compared to traditional CRM training programs. Our future endeavors in training SFRM skills (as well as other organization s) may benefit from adding team performance skills mentoring. This paper explains our mentoring approach and discusses its effectiveness and future applicability in promoting SFRM/CRM skills.
Huning, Therese↗
Predicting Long-Range Traversability from Short-Range Stereo-Derived Geometry
Based only on its appearance in imagery, this program uses close-range 3D terrain analysis to produce training data sufficient to estimate the traversability of terrain beyond 3D sensing range. This approach is called learning from stereo (LFS). In effect, the software transfers knowledge from middle distances, where 3D geometry provides training cues, into the far field where only appearance is available. This is a viable approach because the same obstacle classes, and sometimes the same obstacles, are typically present in the mid-field and the farfield. Learning thus extends the effective look-ahead distance of the sensors.
Turmon, Michael↗
Use of TEMPO as a Proxy for Hyperspectral Geostationary Ocean Color Measurements from the GeoXO OCX Instrument: Harnessing Machine Learning and Principal Component Techniques for Atmospheric and Glint Correction
Retrievals of ocean color from space are important for better understanding the ocean ecosystem. The launch of atmospheric geostationary hyperspectral sensors such as TEMPO, provides a unique opportunity to examine the diurnal variability in ocean ecology. While TEMPO does not have as high spatial resolution or full spectral coverage as planned coastal ocean sensors such as the Geosynchronous Littoral Imaging and Monitoring Radiometer (GLIMR) or GeoXO Ocean Color instrument (OCX), its hourly measurements provide coverage of regions such as Lake Erie and the Gulf of Mexico at spatial scales of approximately 5 km. These data can be useful for testing new algorithms. We will apply our newly developed machine learning based atmospheric correction approach for ocean color retrievals to TEMPO data. Our approach begins by decomposing measured radiances from hyperspectral sensors into spectral features that describe the scattering and absorption of the atmosphere as well as the underlying surface reflectance. The coefficients of the principal components are then used to train a neural network to predict ocean color properties derived from collocated MODIS/VIIRS physically-based retrievals. This machine learning approach does not rely on radiative transfer modeling, and the use of MODIS/VIIRS data for training accounts for possible calibration b in hyperspectral data. Previously, we applied our approach using blue and UV wavelengths with the Ozone Monitoring Instrument (OMI) and TROPOspheric Monitoring Instrument (TROPOMI) to show that it can estimate ocean color properties in less-than-ideal conditions such as lightly to moderately clouded conditions as well as sun glint and thus improve the spatial coverage of ocean color measurements. TEMPO provides an opportunity to improve on this approach since it will provide collocated measurements at green and red wavelengths that were not available from OMI and TROPOMI and are important particularly for coastal waters. Additionally, our technique can be applied early in the mission and has potential to demonstrate the value of near real time ocean color products that are important for monitoring of harmful algae blooms and other oceanic phenomena.
Zachary Fasnacht↗