Search NASA⌕ Search

SEARCH · Search NASA

Results for “Neural encoding”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS1999

Loss tolerant speech decoder for telecommunications

A method and device for extrapolating past signal-history data for insertion into missing data segments in order to conceal digital speech frame errors. The extrapolation method uses past-signal history that is stored in a buffer. The method is implemented with a device that utilizes a finite-impulse response (FIR) multi-layer feed-forward artificial neural network that is trained by back-propagation for one-step extrapolation of speech compression algorithm (SCA) parameters. Once a speech connection has been established, the speech compression algorithm device begins sending encoded speech frames. As the speech frames are received, they are decoded and converted back into speech signal voltages. During the normal decoding process, pre-processing of the required SCA parameters will occur and the results stored in the past-history buffer. If a speech frame is detected to be lost or in error, then extrapolation modules are executed and replacement SCA parameters are generated and sent as the parameters required by the SCA. In this way, the information transfer to the SCA is transparent, and the SCA processing continues as usual. The listener will not normally notice that a speech frame has been lost because of the smooth transition between the last-received, lost, and next-received speech frames.

Prieto, Jr., Jaime L.↗
NASA NTRS2001

A model of cerebellar computations for dynamical state estimation

The cerebellum is a neural structure that is essential for agility in vertebrate movements. Its contribution to motor control appears to be due to a fundamental role in dynamical state estimation, which also underlies its role in various non-motor tasks. Single spikes in vestibular sensory neurons carry information about head state. We show how computations for optimal dynamical state estimation may be accomplished when signals are encoded in spikes. This provides a novel way to design dynamical state estimators, and a novel way to interpret the structure and function of the cerebellum.

NASA Discipline Neuroscience↗
NASA NTRS1986

Parallel structures in human and computer memory

If one thinks of our experiences as being recorded continuously on film, then human memory can be compared to a film library that is indexed by the contents of the film strips stored in it. Moreover, approximate retrieval cues suffice to retrieve information stored in this library. One recognizes a familiar person in a fuzzy photograph or a familiar tune played on a strange instrument. A computer memory that would allow a computer to recognize patterns and to recall sequences the way humans do is constructed. Such a memory is remarkably similiar in structure to a conventional computer memory and also to the neural circuits in the cortex of the cerebellum of the human brain. It is concluded that the frame problem of artificial intelligence could be solved by the use of such a memory if one were able to encode information about the world properly.

Kanerva, P.↗
NASA NTRS1989

Advances in image compression and automatic target recognition; Proceedings of the Meeting, Orlando, FL, Mar. 30, 31, 1989

Various papers on image compression and automatic target recognition are presented. Individual topics addressed include: target cluster detection in cluttered SAR imagery, model-based target recognition using laser radar imagery, Smart Sensor front-end processor for feature extraction of images, object attitude estimation and tracking from a single video sensor, symmetry detection in human vision, analysis of high resolution aerial images for object detection, obscured object recognition for an ATR application, neural networks for adaptive shape tracking, statistical mechanics and pattern recognition, detection of cylinders in aerial range images, moving object tracking using local windows, new transform method for image data compression, quad-tree product vector quantization of images, predictive trellis encoding of imagery, reduced generalized chain code for contour description, compact architecture for a real-time vision system, use of human visibility functions in segmentation coding, color texture analysis and synthesis using Gibbs random fields.

Tescher, Andrew G.↗
NASA NTRS1998

Emulating the visual receptive-field properties of MST neurons with a template model of heading estimation

We have proposed previously a computational neural-network model by which the complex patterns of retinal image motion generated during locomotion (optic flow) can be processed by specialized detectors acting as templates for specific instances of self-motion. The detectors in this template model respond to global optic flow by sampling image motion over a large portion of the visual field through networks of local motion sensors with properties similar to those of neurons found in the middle temporal (MT) area of primate extrastriate visual cortex. These detectors, arranged within cortical-like maps, were designed to extract self-translation (heading) and self-rotation, as well as the scene layout (relative distances) ahead of a moving observer. We then postulated that heading from optic flow is directly encoded by individual neurons acting as heading detectors within the medial superior temporal (MST) area. Others have questioned whether individual MST neurons can perform this function because some of their receptive-field properties seem inconsistent with this role. To resolve this issue, we systematically compared MST responses with those of detectors from two different configurations of the model under matched stimulus conditions. We found that the characteristic physiological properties of MST neurons can be explained by the template model. We conclude that MST neurons are well suited to support self-motion estimation via a direct encoding of heading and that the template model provides an explicit set of testable hypotheses that can guide future exploration of MST and adjacent areas within the superior temporal sulcus.

NASA Discipline Neuroscience↗
NASA NTRS2018

Learning Model Structural Uncertainty with Gaussian Processes

The advent of commercially available quantum computers has marked the beginning of quantum computing as a reality. Both quantum gate and annealing computers have been released by major computer hardware companies. In this work, the D-Wave 2XTM quantum annealing computer housed at the NASA Advanced Systems computational facility is investigated to accelerate Machine Learning (ML) for image registration. NASA collects large amounts of images over the globe remotely using space-based monitoring. Images of a fixed areas of the land surface are taken over time. Due to the orbit of the sensors, the viewing angles deviate slightly, and it is necessary to align or register the images precisely to create image time series over the land surface. Unaligned images can lead to substantial analysis errors. These time-series are then used in modeling Earth Systems models such as hydrological, weather, and carbon monitoring models. In this work, we consider the Moderate Resolution Image Spectrometer (MODIS) data collected by the NASA's terra satellite. Artificial Neural Networks (ANNs) is a natural fit for ML modelling of images. Several successes have been reported using machine learning related to image processing. We investigate the use of ML to register MODIS images. ANNs are investigated in combination with a Restricted Boltzmann Machines (RBM) as an auto-encoder. We will present results showing the accuracy and efficiency of this approach.The D-Wave 2XTM quantum annealer samples the ground-state wave-function of a spin-Ising systems with quadratic interactions between qubits and a Chimera connectivity. The system sits in a ~15 mK thermal bath. One can think of the system as being placed in the ground state initially and subject to thermal excitations governed by Boltzmann statistics. If this is assumed true, one can use the statistics from the D-Wave 2XTM to train RBMs. Generating statistics for training Boltzmann machines is an NP-hard problem and constitutes the largest compute cost. We investigate the use of the D-Wave 2XTM to accelerate the training of the RBMs in our ANNs and report on the results.

Kouatchou, Jules↗
NASA NTRSDate not supplied

Machine Learning Explainability and Transferability for Path Navigation

Deep neural networks are powerful tools for machine perception. Unfortunately their decisions are difficult to explain due to the complexity and size of the networks. Previously we have alleviated this issue by using the representational portion of a deep neural network and combining it with a k-nearest neighbor (KNN) classifier. Through inspection of the decisions made by the KNN, we can directly see the training data responsible for the decisions, allowing us to determine the quality of the overall decision and the quality of the representational layer of the deep NN. While the technique worked well, it requires tens of thousands of latent vectors to be stored for classification. In addition, it lacks the ability to show how parts of an image influence the classification decision. Here we address these issues by 1) Using a radial basis function network (RBFN) in place of the KNN allowing far fewer images to be used in deployment and 2) Using an auto encoder network for explainability. In addition to these techniques, we examine the effects of transfer learning to determine that results are robust. All results are tested on a domain where an unmanned aerial vehicle (UAV) navigates a forest trail through a single camera.

explainable machine learning↗
NASA NTRS2003

Investigation of Neural Strategies of Visual Search

The goal of this project was to measure how neurons in the superior colliculus (SC) change their activity during a visual search task. Specifically, we proposed to measure how the activity of these neurons was altered by the discriminability of visual targets and to test how these changes might predict the changes in the subjects performance. The primary rationale for this study was that understanding how the information encoded by these neurons constrains overall search performance would foster the development of better models of human performance. Work performed during the period supported by this grant has achieved these aims. First, we have recorded from neurons in the superior colliculus (SC) during a visual search task in which the difficulty of the task and the performance of the subject was systematically varied. The results from these single-neuron physiology experiments shows that prior to eye movement onset, the difference in activity across the ensemble of neurons reaches a fixed threshold value, reflecting the operation of a winner-take-all mechanism. Second, we have developed a model of eye movement decisions based on the principle of winner-take-all . The model incorporates the idea that the overt saccade choice reflects only one of the multiple saccades prepared during visual discrimination, consistent with our physiological data. The value of the model is that, unlike previous models, it is able to account for both the latency and the percent correct of saccade choices.

Krauzlis, Richard J.↗
NASA NTRS2003

Generative Representations for Evolving Families of Designs

Since typical evolutionary design systems encode only a single artifact with each individual, each time the objective changes a new set of individuals must be evolved. When this objective varies in a way that can be parameterized, a more general method is to use a representation in which a single individual encodes an entire class of artifacts. In addition to saving time by preventing the need for multiple evolutionary runs, the evolution of parameter-controlled designs can create families of artifacts with the same style and a reuse of parts between members of the family. In this paper an evolutionary design system is described which uses a generative representation to encode families of designs. Because a generative representation is an algorithmic encoding of a design, its input parameters are a way to control aspects of the design it generates. By evaluating individuals multiple times with different input parameters the evolutionary design system creates individuals in which the input parameter controls specific aspects of a design. This system is demonstrated on two design substrates: neural-networks which solve the 3/5/7-parity problem and three-dimensional tables of varying heights.

Hornby, Gregory S.↗
NASA NTRS1995

An Empirical Comparison of Seven Iterative and Evolutionary Function Optimization Heuristics

This report is a repository of the results obtained from a large scale empirical comparison of seven iterative and evolution-based optimization heuristics. Twenty-seven static optimization problems, spanning six sets of problem classes which are commonly explored in genetic algorithm literature, are examined. The problem sets include job-shop scheduling, traveling salesman, knapsack, binpacking, neural network weight optimization, and standard numerical optimization. The search spaces in these problems range from 2368 to 22040. The results indicate that using genetic algorithms for the optimization of static functions does not yield a benefit, in terms of the final answer obtained, over simpler optimization heuristics. Descriptions of the algorithms tested and the encodings of the problems are described in detail for reproducibility.

Baluja, Shumeet↗
NASA NTRS1989

A Cerebellar-model Associative Memory as a Generalized Random-access Memory

A versatile neural-net model is explained in terms familiar to computer scientists and engineers. It is called the sparse distributed memory, and it is a random-access memory for very long words (for patterns with thousands of bits). Its potential utility is the result of several factors: (1) a large pattern representing an object or a scene or a moment can encode a large amount of information about what it represents; (2) this information can serve as an address to the memory, and it can also serve as data; (3) the memory is noise tolerant--the information need not be exact; (4) the memory can be made arbitrarily large and hence an arbitrary amount of information can be stored in it; and (5) the architecture is inherently parallel, allowing large memories to be fast. Such memories can become important components of future computers.

Kanerva, Pentti↗
NASA NTRS2000

Functional conservation of atonal and Math1 in the CNS and PNS

To determine the extent to which atonal and its mouse homolog Math1 exhibit functional conservation, we inserted (beta)-galactosidase (lacZ) into the Math1 locus and analyzed its expression, evaluated consequences of loss of Math1 function, and expressed Math1 in atonal mutant flies. lacZ under the control of Math1 regulatory elements duplicated the previously known expression pattern of Math1 in the CNS (i.e., the neural tube, dorsal spinal cord, brainstem, and cerebellar external granule neurons) but also revealed new sites of expression: PNS mechanoreceptors (inner ear hair cells and Merkel cells) and articular chondrocytes. Expressing Math1 induced ectopic chordotonal organs (CHOs) in wild-type flies and partially rescued CHO loss in atonal mutant embryos. These data demonstrate that both the mouse and fly homologs encode lineage identity information and, more interestingly, that some of the cells dependent on this information serve similar mechanoreceptor functions.

NASA Discipline Developmental Biology↗
NASA NTRS1995

Chimeric Plant Calcium/Calmodulin-Dependent Protein Kinase Gene with a Neural Visinin-Like Calcium-Binding Domain

Calcium, a universal second messenger, regulates diverse cellular processes in eukaryotes. Ca-2(+) and Ca-2(+)/calmodulin-regulated protein phosphorylation play a pivotal role in amplifying and diversifying the action of Ca-2(+)- mediated signals. A chimeric Ca-2(+)/calmodulin-dependent protein kinase (CCaMK) gene with a visinin-like Ca-2(+)- binding domain was cloned and characterized from lily. The cDNA clone contains an open reading frame coding for a protein of 520 amino acids. The predicted structure of CCaMK contains a catalytic domain followed by two regulatory domains, a calmodulin-binding domain and a visinin-like Ca-2(+)-binding domain. The amino-terminal region of CCaMK contains all 11 conserved subdomains characteristic of serine/threonine protein kinases. The calmodulin-binding region of CCaMK has high homology (79%) to alpha subunit of mammalian Ca-2(+)/calmodulin-dependent protein kinase. The calmodulin-binding region is fused to a neural visinin-like domain that contains three Ca-2(+)-binding EF-hand motifs and a biotin-binding site. The Escherichia coli-expressed protein (approx. 56 kDa) binds calmodulin in a Ca-2(+)-dependent manner. Furthermore, Ca-45-binding assays revealed that CCaMK directly binds Ca-2(+). The CCaMK gene is preferentially expressed in developing anthers. Southern blot analysis revealed that CCaMK is encoded by a single gene. The structural features of the gene suggest that it has multiple regulatory controls and could play a unique role in Ca-2(+) signaling in plants.

Patil, Shameekumar↗
NASA NTRS2005

Cerebellum Augmented Rover Development

Bio-Inspired Technologies and Systems (BITS) are a very natural result of thinking about Nature's way of solving problems. Knowledge of animal behaviors an be used in developing robotic behaviors intended for planetary exploration. This is the expertise of the JFL BITS Group and has served as a philosophical model for NMSU RioRobolab. Navigation is a vital function for any autonomous system. Systems must have the ability to determine a safe path between their current location and some target location. The MER mission, as well as other JPL rover missions, uses a method known as dead-reckoning to determine position information. Dead-reckoning uses wheel encoders to sense the wheel's rotation. In a sandy environment such as Mars, this method is highly inaccurate because the wheels will slip in the sand. Improving positioning error will allow the speed of an autonomous navigating rover to be greatly increased. Therefore, local navigation based upon landmark tracking is desirable in planetary exploration. The BITS Group is developing navigation technology based upon landmark tracking. Integration of the current rover architecture with a cerebellar neural network tracking algorithm will demonstrate that this approach to navigation is feasible and should be implemented in future rover and spacecraft missions.

King, Matthew↗
NASA NTRS2000

Evolutionary conservation of the presumptive neural plate markers AmphiSox1/2/3 and AmphiNeurogenin in the invertebrate chordate amphioxus

Amphioxus, as the closest living invertebrate relative of the vertebrates, can give insights into the evolutionary origin of the vertebrate body plan. Therefore, to investigate the evolution of genetic mechanisms for establishing and patterning the neuroectoderm, we cloned and determined the embryonic expression of two amphioxus transcription factors, AmphiSox1/2/3 and AmphiNeurogenin. These genes are the earliest known markers for presumptive neuroectoderm in amphioxus. By the early neurula stage, AmphiNeurogenin expression becomes restricted to two bilateral columns of segmentally arranged neural plate cells, which probably include precursors of motor neurons. This is the earliest indication of segmentation in the amphioxus nerve cord. Later, expression extends to dorsal cells in the nerve cord, which may include precursors of sensory neurons. By the midneurula, AmphiSox1/2/3 expression becomes limited to the dorsal part of the forming neural tube. These patterns resemble those of their vertebrate and Drosophila homologs. Taken together with the evolutionarily conserved expression of the dorsoventral patterning genes, BMP2/4 and chordin, in nonneural and neural ectoderm, respectively, of chordates and Drosophila, our results are consistent with the evolution of the chordate dorsal nerve cord and the insect ventral nerve cord from a longitudinal nerve cord in a common bilaterian ancestor. However, AmphiSox1/2/3 differs from its vertebrate homologs in not being expressed outside the CNS, suggesting that additional roles for this gene have evolved in connection with gene duplication in the vertebrate lineage. In contrast, expression in the midgut of AmphiNeurogenin together with the gene encoding the insulin-like peptide suggests that amphioxus may have homologs of vertebrate pancreatic islet cells, which express neurogenin3. In addition, AmphiNeurogenin, like its vertebrate and Drosophila homologs, is expressed in apparent precursors of epidermal chemosensory and possibly mechanosensory cells, suggesting a common origin for protostome and deuterostome epidermal sensory cells in the ancestral bilaterian. Copyright 2000 Academic Press.

NASA Discipline Evolutionary Biology↗
NASA NTRS1991

Experiments on neural network architectures for fuzzy logic

The use of fuzzy logic to model and manage uncertainty in a rule-based system places high computational demands on an inference engine. In an earlier paper, the authors introduced a trainable neural network structure for fuzzy logic. These networks can learn and extrapolate complex relationships between possibility distributions for the antecedents and consequents in the rules. Here, the power of these networks is further explored. The insensitivity of the output to noisy input distributions (which are likely if the clauses are generated from real data) is demonstrated as well as the ability of the networks to internalize multiple conjunctive clause and disjunctive clause rules. Since different rules with the same variables can be encoded in a single network, this approach to fuzzy logic inference provides a natural mechanism for rule conflict resolution.

Keller, James M.↗
NASA NTRSDate not supplied

Impact Ice Microstructure Segmentation Using Transfer Learned Model

A process of using machine learning to segment impact ice microstructure is presented and analyzed. The segmentation was conducted with the goal of obtaining average grain size estimations. The model was trained on a set of micrographs of impact ice grown at NASA Glenn’s Icing Research Tunnel. The model leveraged a model pre-trained on a large set of micrographs of various materials as a starting point. Post-processing of the segmented images was done to connect broken boundaries. An automatic method of determining grain size following an ASTM standard was implemented. Segmentation results using different training sets as well as different encoder and decoder pairs are presented. Calculated sizes are compared to manual grain size measurement methods. Results show promise in accuracy as well as a possible improvement in repeatability and consistency. Next steps for improving the model are suggested.

Machine learning↗
NASA NTRS2020

Convolutional Neural Network for Transition Modeling Based on Linear Stability Theory

Transition prediction is an important aspect of aerodynamic design because of its impact on skin friction and potential coupling with flow separation characteristics. Traditionally, the modeling of transition has relied on correlation-based empirical formulas based on integral quantities such as the shape factor of the boundary layer. However, in many applications of computational fluid dynamics, the shape factor is not straightforwardly available or not well-defined. We propose using the complete velocity profile along with other quantities (e.g., frequency, Reynolds number) to predict the perturbation amplification factor. While this can be achieved with regression models based on a classical fully connected neural network, such a model can be computationally more demanding. We propose a novel convolutional neural network inspired by the underlying physics as described by the stability equations. Specifically, convolutional layers are first used to extract integral quantities from the velocity profiles, and then fully connected layers are used to map the extracted integral quantities, along with frequency and Reynolds number, to the output (amplification ratio). Numerical tests on classical boundary layers clearly demonstrate the merits of the proposed method. More importantly, we demonstrate that, for Tollmien-Schlichting instabilities in two-dimensional, low-speed boundary layers, the proposed network encodes information in the boundary layer profiles into an integral quantity that is strongly correlated to a well-known, physically defined parameter – the shape factor.

Laminar-turbulent transition↗