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 46 for “"Residual Neural Network"”.

  1. Vehicle Detection in Deep Learning

    … detection model, adopting one of the classical neural networks, which are the residual neural network and the region proposal network. The model utilizes the residual neural network as a feature extractor and the region proposal network to detect the potential objects' information.

    vt Repository record for Vehicle Detection in Deep Learning (opens in a new tab)

  2. Late residual neural networks: an approach to combat the dead ReLU problem

    … learning to increase the performance of deep neural network architectures. However, the ReLU activation function has trade-offs with its performance, specifically the dead ReLU problem caused by vanishing gradients. In this thesis, we introduce "late residual connections" a type of residual …

    colostate Repository record for Late residual neural networks: an approach to combat the dead ReLU problem (opens in a new tab)

  3. Bird Species Identification using Convolutional Neural Networks

    … as a baseline. The questions asked are: Can deep residual neural networks learn to classify bird species based on bird song and how well to they perform? Do multiple-width frequency-delta data augmentation or meta-data fusion further increase the accuracy of the model? The questions are answered …

    chalmers Repository record for Bird Species Identification using Convolutional Neural Networks (opens in a new tab)

  4. RNN-Enhanced Deep Residual Neural Networks for Web Page Classification

    … results. We introduce a relatively deep residual neural network for Web page classification problem based on the simplified version of the target HTML document. Combining several advanced techniques of deep learning, the optimal model has 20 neural layers with parameters, and is …

    calgary Repository record for RNN-Enhanced Deep Residual Neural Networks for Web Page Classification (opens in a new tab)

  5. ANALYSIS OF CELL MORPHOMETRIC PHENOTYPES BY DEEP LEARNING

    … fluorescence micrographs, termed SE-RNN (residual neural network with squeeze-and-excite blocks). We demonstrate SERNN-based classification of distinct morphological signatures observed when fibroblasts or epithelial cells are presented with different ECM. We also demonstrate that …

    nus Repository record for ANALYSIS OF CELL MORPHOMETRIC PHENOTYPES BY DEEP LEARNING (opens in a new tab) Download file for ANALYSIS OF CELL MORPHOMETRIC PHENOTYPES BY DEEP LEARNING (opens in a new tab)

  6. Sparse Neural Network to Enhance Performance Under Limited Parameter Constraints.

    … the past decade, the widespread adoption of deep neural networks has been a breakthrough driven by significant computational advancements. Additionally, the number of parameters of those models is exponentially increasing for performing complex tasks and achieving better performance. However, in …

    arkansas Repository record for Sparse Neural Network to Enhance Performance Under Limited Parameter Constraints. (opens in a new tab)

  7. Toward Utilizing Analog Rydberg Atom Systems for Quantum Machine Learning

    … implementation of quantum generative adversarialnetworks (GANs) on analog Rydberg atom quantum computers, achieving a 33% improvement in image generation quality (measured via Frechet Inception Distance) compared to state-of-the-art superconducting-qubit techniques. Second, we introduce ResQ, a …

    rice Repository record for Toward Utilizing Analog Rydberg Atom Systems for Quantum Machine Learning (opens in a new tab)

  8. Neural Modelling of Astrophysical Gas

    We investigate the abilities of neural models to model astrophysical gases, addressing limitations in traditional numerical solvers such as energy bottlenecks, resolution effects, grid anisotropy effects, and strict time-stepping constraints. In particular, we focus on simulations of turbulent …

    mcmaster Repository record for Neural Modelling of Astrophysical Gas (opens in a new tab)

  9. Modeling Nonlinear Dynamic Systems Using BSS-ANOVA Gaussian Process

    … is compared to the results of a Random Forest, a Residual Neural Network, and an Orthogonalized Additive Kernel (OAK) inducing point GP. The dynamic time series predictions are compared to the GRU and LSTM Recurrent Neural Networks (RNN), as well as SINDy. For the static predictions, the BSS-ANOVA …

    wvu Repository record for Modeling Nonlinear Dynamic Systems Using BSS-ANOVA Gaussian Process (opens in a new tab)

  10. Exploring Emotion Recognition of Students in Virtual Reality Classrooms Through Convolutional Neural Networks and Transfer Learning Techniques

    … paper explores the potential of Convolutional Neural Networks (CNNs), specifically a customized training approach model adapted from the ResNet50 architecture, in recognizing and distinguishing subtle facial expressions in real-time, such as neutrality, boredom, happiness, and confusion. The …

    calgary Repository record for Exploring Emotion Recognition of Students in Virtual Reality Classrooms Through Convolutional Neural Networks and Transfer Learning Techniques (opens in a new tab)

  11. Deep residual networks for wireless transmitter localization using sparse boundary measurements

    … challenge in wireless communication, impacting network optimization, security, and spectrum management. Traditional localization techniques, such as triangulation and fingerprinting, require extensive data collection and computational resources, making them impractical for large-scale …

    ets-quebec Download PDF for Deep residual networks for wireless transmitter localization using sparse boundary measurements (opens in a new tab)

  12. Performance Evaluation of 5G MIMO DetectorsWith Deep Learning

    Fifth-generation (5G) wireless networks promise ultra-reliable low-latency communication, enhanced mobile broadband, and massive machine-type connectivity capabilities made possible by advanced technologies such as massive MIMO, OFDM-based modulation, and dynamic spectrum access. However, these …

    concordia Download PDF for Performance Evaluation of 5G MIMO DetectorsWith Deep Learning (opens in a new tab)

  13. EMULATING PASSIVE MICROWAVE OBSERVATIONS WITH PATCH-TO-PIXEL CONVOLUTIONAL NEURAL NETWORKS

    … sampling in conjunction with a purpose-built Residual Neural Network to perform regression from multi-spectral ABI data to a single GMI channel. In doing so, we prove that it is possible to predict under-represented values more accurately in datasets when using our sampling method and to …

    nps Repository record for EMULATING PASSIVE MICROWAVE OBSERVATIONS WITH PATCH-TO-PIXEL CONVOLUTIONAL NEURAL NETWORKS (opens in a new tab)

  14. Machine Learning Methods for Sound Power Minimization

    … sound power design optimization. First, a residual neural network was trained using supervised learning to estimate the broadband average sound power of a specified design. The first method implemented the residual network into a traditional topology optimization framework to perform the …

    queens Repository record for Machine Learning Methods for Sound Power Minimization (opens in a new tab)

  15. Partial Discharges: Experimental Investigation, Model Development, and Data Analytics

    … For the second target, it is aimed to use deep neural networks to identify and discriminate different sources of PD. The measurement data are used to generate thousands of phase-resolved PD (PRPD) images that will be used for training deep learning models. To meet the characteristics of the …

    vt Repository record for Partial Discharges: Experimental Investigation, Model Development, and Data Analytics (opens in a new tab)

  16. Soft labels and supervised image classification

    … dire consequences. Adversarial attacks on deep neural networks exploit instabilities in the network with regard to noise and thus are important problems in the field of machine learning. In recent years, much attention has been given to the design of architectures and procedures that help …

    ubc Repository record for Soft labels and supervised image classification (opens in a new tab) Download PDF for Soft labels and supervised image classification (opens in a new tab)

  17. Improving Presentation Consistency of Radiographic Images Using Deep Learning

    … the consistency in presentation by using a residual neural network trained to classify X-ray images based on a novel NxM grid of brightness and contrast combinations is proposed. More than 8,500 unique images from sites in US, Ireland and Sweden covering 27 anatomy/view combinations were …

    marquette Repository record for Improving Presentation Consistency of Radiographic Images Using Deep Learning (opens in a new tab)

  18. Keyword Spotting Within an Automotive Environment

    … model was found to be a temporal convolutional residual neural network (TC-ResNet) using mel frequency cepstral coefficients (MFCC) features, which achieved an accuracy of 95.34% on the validation dataset. The model complexity is low compared to models in previous studies, with 152.7 K …

    chalmers Repository record for Keyword Spotting Within an Automotive Environment (opens in a new tab)

  19. Utilization of Deep-Learning Algorithms for Bias-Correction and Forecasting of Weather, Air Quality, and Climate Parameters Over Regional Scales

    … bias correction methods, Autoencoder-Decoder and Residual Neural Network (ResNet) were applied to CORDEX-SA climatic simulations. Using eight meteorological variables and digital elevation data at 0.25° resolution as input, the models generated bias-corrected precipitation at 0.05° resolution. The …

    houston Repository record for Utilization of Deep-Learning Algorithms for Bias-Correction and Forecasting of Weather, Air Quality, and Climate Parameters Over Regional Scales (opens in a new tab) Embargoed until 2027-12-01

  20. Attention-based deep neural networks for the forecasting and reconstruction of an environmental image series

    … Although the convolutional layer in this network can capture the local spatial dependencies, the network fails to extract global interactions among hidden features in the date. Moreover, in order to interpret the associated environmental field, a Kriging approach may be utilized in the …

    ubc Repository record for Attention-based deep neural networks for the forecasting and reconstruction of an environmental image series (opens in a new tab) Download PDF for Attention-based deep neural networks for the forecasting and reconstruction of an environmental image series (opens in a new tab)

Page 1 of 3