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 245 for “"learning networks"”.

  1. Learning networks via non-invasive observations

    Learning the underlying structure of a networked dynamic system from observational data is an important problem in many domains, from climate studies to economics. One of the most well-known approaches to this problem is Granger causality, which relies on the premise that data are sampled at a …

    umn Repository record for Learning networks via non-invasive observations (opens in a new tab)

  2. MELANOMA DETECTION BASED ON DEEP LEARNING NETWORKS

    … team introduces a sophisticated transfer learning model that utilizes Resnet50 to classify melanoma. Transfer learning is a machine learning technique that takes advantage of trained models, for similar tasks resulting in time saving and enhanced accuracy by avoiding the need to train from …

    csusb Repository record for MELANOMA DETECTION BASED ON DEEP LEARNING NETWORKS (opens in a new tab)

  3. Optimizing deep learning networks using multi-armed bandits

    Deep learning has gained significant attention recently following their successful use for applications such as computer vision, speech recognition, and natural language processing. These deep learning models are based on very large neural networks, which can require a significant amount of memory …

    salford Download PDF for Optimizing deep learning networks using multi-armed bandits (opens in a new tab)

  4. Application of deep learning networks to crime prediction

    … prevention. This thesis discuss the use of deep learning networks, an advanced machine learning technique, as applied to the task of predicting future crimes. First, an extensive set of experiments of various types of network structures, together with various pre-processing dimension-reduction …

    missouri Repository record for Application of deep learning networks to crime prediction (opens in a new tab)

  5. Deep weakly supervised learning networks for object localization

    … image analysis. Recent advances in deep neural networks have yielded significant improvements in these tasks. However, the success of these models is heavily attributed to the large amount of annotated data, which are costly and time-consuming to acquire. Additionally, this paradigm is not …

    ets-quebec Download PDF for Deep weakly supervised learning networks for object localization (opens in a new tab)

  6. Adversarial Example Resistant Hyperparameters and Deep Learning Networks

    … shown to cause misclassifications in machine learning based classification systems resulting in the phenomenon of adversarial examples. Hyperparameters, the settings used to build and train machine learning models, have been shown to build machine learning models that are more resistant to …

    washington Repository record for Adversarial Example Resistant Hyperparameters and Deep Learning Networks (opens in a new tab)

  7. Cortex-inspired developmental learning networks for stereo vision

    … e.g., under weak textures. Developmental networks, such as Where-What Networks (WWN), have been shown promising for simultaneous attention and recognition, while handling variations in scale, location and type as well as inter-class variations. Moreover, in a simpler prior setting, they …

    msu Repository record for Cortex-inspired developmental learning networks for stereo vision (opens in a new tab)

  8. Multi-instance learning networks for flow cytometry data analysis

    … comprehensively. This thesis establishes deep learning networks to provide an end-to-end way for FCM analysis based on numerous biomarker- ers. Compared with previous analytical approaches, networks are designed in a multi-instance learning manner specific for FCM analysis, where an instance …

    jhu Repository record for Multi-instance learning networks for flow cytometry data analysis (opens in a new tab)

  9. Unbiased Representation Learning Networks for Single Rainy Image Restoration

    … However, by evaluating representative deep-learning based deraining models on benchmark datasets, two unfavorable results are obtained: (1) they cannot handle various rainy conditions (i.e., rains of various directions and densities) equally well, and (2) the models trained on synthetic …

    unsw Repository record for Unbiased Representation Learning Networks for Single Rainy Image Restoration (opens in a new tab)

  10. Music Learning Networks: Supporting the Music Learning of Adolescents

    … shifting availability of formal and virtual learning opportunities, and the increasingly diverse group of young musicians engaging with music today are all drivers of this evolution. To better understand how young people learn music of personal significance, I adapted elements from …

    washington Repository record for Music Learning Networks: Supporting the Music Learning of Adolescents (opens in a new tab)

  11. Mud and Cell Phones: Nonformal Learning Networks in Rural Kenya

    … millions of people still lack access to learning, with a high concentration in sub-Saharan African countries. Like many rural communities around the world, Kenya’s rural population experiences challenges in accessing resources and opportunities equal to those living in urban centers. With …

    waterloo Repository record for Mud and Cell Phones: Nonformal Learning Networks in Rural Kenya (opens in a new tab)

  12. An evolutionary method for training autoencoders for Deep Learning Networks

    Introduced in 2006, Deep Learning has made large strides in both supervised an unsupervised learning. The abilities of Deep Learning have been shown to beat both generic and highly specialized classification and clustering techniques with little change to the underlying concept of a multi-layer …

    missouri Repository record for An evolutionary method for training autoencoders for Deep Learning Networks (opens in a new tab)

  13. Detection of human face from sketches using deep learning networks

    … specifically, the recent state of the art deep learning techniques to identify people based on their sketches for law and enforcement. The dataset is collected from Chinese database (CUHK student dataset) that includes both photos and their corresponding sketches. The sketches are drawn by …

    middlesex Download PDF for Detection of human face from sketches using deep learning networks (opens in a new tab)

  14. How Principals Cultivate Technology Integration and Use Professional Learning Networks

    … integrating technology in teaching and learning were examined. Also, ways in which principals utilize social and technological learning networks to support professional learning and growth were also explored. Interview and survey data from principals and teachers in three school …

    calgary Repository record for How Principals Cultivate Technology Integration and Use Professional Learning Networks (opens in a new tab)

  15. Deep learning networks for automatic brain tumour segmentation from MRI data

    … presents novel image processing and deep learning methods for automatic brain tumour regions segmentation from MRI data. The MRI data of brain tumour patients from Brain Tumour Segmentation or BraTS dataset from 2018-2021 are used in this study. 2D deep neural networks for semantic …

    strathclyde Repository record for Deep learning networks for automatic brain tumour segmentation from MRI data (opens in a new tab)

  16. Graph-based Learning Networks for Automatic Pigment Mapping of Historical Artifacts

    … varied pigments, we introduce graph- based learning networks and a powerful learning pipeline for realizing automatic pigment mapping on the maps. First, we develop a Graph Modularity clustering method for pro- ducing trustworthy ground-truth map for pigment classification task. We analyze …

    rit Repository record for Graph-based Learning Networks for Automatic Pigment Mapping of Historical Artifacts (opens in a new tab)

  17. Primary strategy learning networks: a local study of a national initiative

    … of one such initiative – Primary Strategy Learning Networks (DfES, 2004a). The research focuses on a reliance on school networks as power bases for promoting a national standards agenda. It considers the impact of an imposed model of school collaboration on the fluid nature of networking. …

    birmingham Download PDF for Primary strategy learning networks: a local study of a national initiative (opens in a new tab)

  18. Digital Bridges: How Art Educators Build Professional Learning Networks on Twitter

    … in the #K12ArtChat, as a form of professional learning. Grounded in social constructivist learning, connectivism, and informal learning, this study addressed how and why art educators use Twitter Chats for professional growth and the potential impact of participation on their teaching …

    kennesaw Repository record for Digital Bridges: How Art Educators Build Professional Learning Networks on Twitter (opens in a new tab)

Page 1 of 13