Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 56 for “"Sparse network"”.

  1. Empirical Study of Two Hypothesis Test Methods for Community Structure in Networks

    Many real-world network data can be formulated as graphs, where a binary relation exists between nodes. One of the fundamental problems in network data analysis is community detection, clustering the nodes into different groups. Statistically, this problem can be formulated as hypothesis testing: …

    ndsu Repository record for Empirical Study of Two Hypothesis Test Methods for Community Structure in Networks (opens in a new tab)

  2. COMPETITIVE STRATEGY, ALLIANCE NETWORKS, AND FIRM PERFORMANCE

    … between competitive strategy and alliance network structure in explaining firm performance in highly volatile environments (e.g., personal computers or consumer electronics). In particular, I examine the following three questions: (1) Which competitive strategies enable firms to gain …

    uky-thes Repository record for COMPETITIVE STRATEGY, ALLIANCE NETWORKS, AND FIRM PERFORMANCE (opens in a new tab)

  3. An Investigation of the Interactions of Gradient Coherence and Network Pruning in Neural Networks

    … on real and random data regardless of the network's initialization. We introduce "diffs," an attempt at an element-wise approximation at coherence, and investigate their properties. We study how coherence is affected by increasing the width of simple fully-connected networks. We then prune …

    byu Repository record for An Investigation of the Interactions of Gradient Coherence and Network Pruning in Neural Networks (opens in a new tab) Download PDF for An Investigation of the Interactions of Gradient Coherence and Network Pruning in Neural Networks (opens in a new tab)

  4. Spatial and temporal trends of snow cover properties in a large subarctic basin: implications for basin-wide, end-of-winter snow water equivalent estimates

    … For large basins, SWE is often estimated using a sparse network of sites. In this study, historical snow surveys (1978-2017) conducted across the 13,700 km2 Snare River basin near Yellowknife, NWT, were analyzed to identify local and regional scales of variability as well as temporal trends. Two …

    carleton Repository record for Spatial and temporal trends of snow cover properties in a large subarctic basin: implications for basin-wide, end-of-winter snow water equivalent estimates (opens in a new tab)

  5. Linear and Nonlinear Topology Optimization with Morphing Beam Networks

    … structures frequently resemble sparsely arranged beams, we propose to replace the initial domain of solid elements with a sparse network of morphing beam elements to largely reduce the computational cost while retaining the result fidelity. Although the substitution of solid …

    clemson Repository record for Linear and Nonlinear Topology Optimization with Morphing Beam Networks (opens in a new tab)

  6. Trustworthy and Efficient Knowledge Sharing across Tasks in Deep Neural Networks

    Deep neural networks (DNNs) have revolutionized various fields with their superior performance on particular tasks. However, these tasks in real-world applications are often interrelated, raising the necessity for DNNs to share and transfer knowledge reliably and effectively between tasks. To solve …

    uts Repository record for Trustworthy and Efficient Knowledge Sharing across Tasks in Deep Neural Networks (opens in a new tab)

  7. Downlink Transmissions for Millimeter-Wave MIMO Networks with Reconfigurable Antenna Arrays

    … beamforming. In this work, we analyze the network performance in two practical scenarios of mmWave networks. We develop an antenna array reconfiguration structure in the analog domain with low hardware complexity. We propose analog beamforming strategies to improve the spectral efficiency …

    rice Repository record for Downlink Transmissions for Millimeter-Wave MIMO Networks with Reconfigurable Antenna Arrays (opens in a new tab)

  8. Assimilation of Time-averaged Pseudoproxies for Climate Reconstruction

    … reconstructing surface temperature fields from a sparse network of noisy pseudoproxies. We compare the DA approach to a conventional CFR approach based on Principal Component Analysis (PCA) for experiments on global domains. DA outperforms PCA in reconstructing global-mean temperature in all four …

    washington Repository record for Assimilation of Time-averaged Pseudoproxies for Climate Reconstruction (opens in a new tab)

  9. Sparse weight activation training

    Neural network training is computationally and memory intensive. Sparse training can reduce the burden, but it can affect network convergence. In this work, we propose a novel CNN training algorithm Sparse Weight Activation Training (SWAT). SWAT is : (1) more computation and memory-efficient than …

    ubc Repository record for Sparse weight activation training (opens in a new tab) Download PDF for Sparse weight activation training (opens in a new tab)

  10. Balancing Multiple Goals In Observational Study Design

    … computational efficiency through the use of a sparse network representation. The second chapter defines a class of variables called prods which can be ignored when matching in order to strictly attenuate unmeasured bias, if it is present. These variables can be difficult to identify with …

    penn Repository record for Balancing Multiple Goals In Observational Study Design (opens in a new tab)

  11. Sparse deep neural networks for modeling physical and biological systems

    Characterizing the relationship between network performance and its parameters is an active area of investigation within the fields of deep learning and complex network science. In this thesis, sparse deep neural networks (DNNs) are explored as tools for modeling physical and biological systems and …

    washington Repository record for Sparse deep neural networks for modeling physical and biological systems (opens in a new tab)

  12. Some inverse problems on finite networks

    … Alternating Current (AC) and Direct Current (DC) networks. From the definition of the tangent space at each vertex of the network, we can define discrete concepts that mimic the continuous differential operators, vector fields or boundary value problems. This discrete vector calculus provides a …

    valladolid Repository record for Some inverse problems on finite networks (opens in a new tab)

  13. Machine Learning for Information Extraction

    … classification problem, and applies the SNOW (Sparse Network of Winnows) learning system to learn a part of speech classifier. A comprehensive experimental evaluation of the system confirms that it is appropriate for NLP applications. The dissertation addresses the problem of entity extraction …

    uiuc Repository record for Machine Learning for Information Extraction (opens in a new tab)

  14. Orchestrating economic development: exploring interorganizational networks in the Chicago metro area

    … the Chicago metro area by exploring the social network structure of cooperation, the conditions under which local governments cooperate and the resulting outcomes of cooperation. The results suggests that communities in the Chicago metro area are spatially aware of the roles of neighboring …

    uiuc Repository record for Orchestrating economic development: exploring interorganizational networks in the Chicago metro area (opens in a new tab)

  15. Remote triggering of microseismicity in Antarctica by large distant earthquakes

    … have been done in Antarctica, mostly due to sparse network coverage. Since 2007, a new generation of broadband sensors has been deployed as permanent stations throughout Antarctica (POLENET project). This, together with other permanent and temporary seismic stations, provides critical …

    gatech Repository record for Remote triggering of microseismicity in Antarctica by large distant earthquakes (opens in a new tab)

  16. Modeling and characterization of photoresponse of nanowires with asymmetric contacts and bending strain

    … and characterization, we show that nanowire networks with dual-metal contacts produce large photo currents. Interestingly, a sparse network gives larger response than a relatively dense network. High resistance nanowire-nanowire contact is shown to place a limit on electrical transport and …

    washington Repository record for Modeling and characterization of photoresponse of nanowires with asymmetric contacts and bending strain (opens in a new tab)

  17. The use of Meteosat satellite data for spatial rainfall estimations and hydrological simulations

    … using both the measurements from a dense and sparse network of rain-gauges and images from the meteorological satellites. A primary concern is to study the effects of such satellite assisted rainfall estimates on the performance of rainfall-runoff models. Low-cost image processing systems and …

    aston Download PDF for The use of Meteosat satellite data for spatial rainfall estimations and hydrological simulations (opens in a new tab)

  18. Learning Temporal Social Graphs for Cyberbullying Prediction

    … behavior remains challenging, particularly in sparse network settings where explicit user interactions are limited, linguistic patterns vary across domains, and temporal dynamics shape abusive behaviors over time. Existing methods, which often rely on textual content, user profiles, or static …

    unsw Repository record for Learning Temporal Social Graphs for Cyberbullying Prediction (opens in a new tab)

  19. Modeling Social Network Change over Time: A Comparison of Methods

    … assessing prevalence of using analytical social network methods in educational research, 2) being the first to directly compare four possible approaches for modeling longitudinal stochastic social networks: temporal exponential random graph model with bootstrapping (TERGM-B), temporal exponential …

    washington Repository record for Modeling Social Network Change over Time: A Comparison of Methods (opens in a new tab)

  20. On Compressing Deep Neural Networks

    Though deep neural networks achieve great accuracy in visual recognition tasks, they contain millions of weights and thus require a large space to be stored. In this dissertation, we focus on compressing different types of deep neural networks in different situations. First, we present a novel deep …

    wayne-thes Repository record for On Compressing Deep Neural Networks (opens in a new tab)

Page 1 of 3