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 135 for “"ResNet50"”.

  1. Chest Disease Classification using Transfer Learning

    … and transfer learning, with a prime focus on the RESNET50 architecture. The primary objective is to develop a model which is intelligent enough to detect various chest conditions, including COVID- 19, viral pneumonia, bacterial pneumonia, and normal cases. Utilizing the rigorously pre-trained …

    rit Repository record for Chest Disease Classification using Transfer Learning (opens in a new tab)

  2. Sensitivity of Feedforward Neural Networks to Harsh Computing Environments

    … to be on par with random guessing. VGG16, ResNet50, and InceptionV3 were also tested for their robustness. ResNet50 and InceptionV3 were both more robust than VGG16. This could be due to their use of Batch Normalization or the fact that ResNet50 and InceptionV3 both use shortcut connections …

    vt Repository record for Sensitivity of Feedforward Neural Networks to Harsh Computing Environments (opens in a new tab)

  3. Neuroninių tinklų palyginimas rentgeno nuotraukų atpažinimui /

    … neural network models VGG16, DenseNet121 and ResNet50. Graphs depicting their results were formed according to which the calculation models of similarity metrics based on triplet neural networks were compared. The results of the different groups of images they achieved and their totality were …

    vilnius Repository record for Neuroninių tinklų palyginimas rentgeno nuotraukų atpažinimui / (opens in a new tab)

  4. Crop disease detection using deep learning techniques on images

    … Architectures such as AlexNet and GoogleNet, ResNet50 and InceptionV3 are used. Two approaches are used to train the model: ‘training from scratch’ and ‘transfer learning’. It was found from the results of the primary analysis that the GoogleNet leaves behind the AlexNet, ResNet50 and …

    laurentian Repository record for Crop disease detection using deep learning techniques on images (opens in a new tab)

  5. Improved Deep Learning Model Based on Integrated Convolutional Neural Networks and Transfer Learning for Shoeprint Image Classification

    … different pre-trained Inception V3, VGG16, and ResNet50 models. The results show that convolutional neural networks-transfer learning (CNN-TL) improved classification accuracy by approximately 3% compared to conventional convolutional neural networks (CNN). The study employed three techniques …

    auckland-tech Repository record for Improved Deep Learning Model Based on Integrated Convolutional Neural Networks and Transfer Learning for Shoeprint Image Classification (opens in a new tab)

  6. MELANOMA DETECTION BASED ON DEEP LEARNING NETWORKS

    … 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 scratch. The Resnet50 is a …

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

  7. Redes neurais profundas para identificação de ritmo em músicas de forró: uma abordagem exploratória rumo à inclusão de dançarinos surdos

    … Network (DenseNet121) e Residual Network (ResNet50), com diferentes configurações de entrada para reduzir o erro na estimação da DPB. O treinamento e a avaliação utilizaram métricas de Erro Quadrático Médio (EQM), Erro Percentual Absoluto Médio (EPAM) e correlação de Pearson, com folds …

    brazil-ufv Repository record for Redes neurais profundas para identificação de ritmo em músicas de forró: uma abordagem exploratória rumo à inclusão de dançarinos surdos (opens in a new tab)

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

    … 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 novelty of our approach is twofold: First, we optimize the power of CNNs to analyze facial …

    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)

  9. Optimization of Deep Neural Networks for Efficient Resource Utilization

    … Training (QAT) were applied to MobileNetV2 and ResNet50 for classification on the Mini-ImageNet dataset, and to FCN-ResNet18 for segmentation on the Cityscapes dataset. Additionally, mixed-precision QAT was investigated using first-order gradient-based sensitivity analysis to assign per-layer …

    chalmers Repository record for Optimization of Deep Neural Networks for Efficient Resource Utilization (opens in a new tab)

  10. Vaistų atpažinimas naudojant gilųjį mokymąsi /

    … of a convolutional neural network based on the ResNet50 model used in one of the previous studies by using more modern models from the EfficientNet family with a different architecture. In addition, a system that adjusts the size of a picture of a drug using a coin as a reference before …

    vilnius Repository record for Vaistų atpažinimas naudojant gilųjį mokymąsi / (opens in a new tab)

  11. GAUSSIAN PROCESSES FOR SATELLITE DATA

    … to train than traditional CNNs. We train a ResNet50 CNN augmented with GPs against a large satellite dataset but test the model across not only held out data from the training dataset but also two other large datasets of a tropical cyclone and mesoscale convective system to test model …

    nps Repository record for GAUSSIAN PROCESSES FOR SATELLITE DATA (opens in a new tab)

  12. Hybrid Compression: Exploiting Model and Data Compression for Deep Neural Network Workloads

    … point operations (FLOPs) of MobileNetV1 and ResNet50 respectively. Starting from models which are pruned 50% FLOPs, hybrid compression can achieve compression ratio of 6.29 and 7.53, speedup of 2.74 and 4.21 and with accuracy drop of 7.71% and 9.27% for MobileNetV1 and ResNet50. To verify the …

    chalmers Repository record for Hybrid Compression: Exploiting Model and Data Compression for Deep Neural Network Workloads (opens in a new tab)

  13. Satellite Image Analysis and Sidewalk Classification using Deep Learning Models

    … using pretrained CNN models including VGG16 and ResNet50. I extended these models by adding custom layers at the top of pretrained layers, employing various techniques to improve the classification accuracy. The dataset comprises 4,731 images of sidewalk based on occlusion levels, including …

    usm Repository record for Satellite Image Analysis and Sidewalk Classification using Deep Learning Models (opens in a new tab)

  14. Rozpoznání druhu vozidla v obraze

    … sietí boli použité architektúry: VGG16, ResNet50, Xception, InceptionResNet-v2. Výsledkom práce je porovnanie architektúr. Všetky architektúry sa natrénovali a dosiahli výsledok nad 90%.

    brno-tech Repository record for Rozpoznání druhu vozidla v obraze (opens in a new tab)

  15. Defect Detection of Photovoltaic Panels by Image Processing

    … Convolutional neural network (CNN). We will use ResNet50. ResNet50 is a convolutional neural network (CNN). It is a specific architecture within the CNN family that is designed for tasks related to computer vision, such as image classification, object detection, and image segmentation. The …

    rit Repository record for Defect Detection of Photovoltaic Panels by Image Processing (opens in a new tab)

  16. An analytical framework of tissue-patch clustering for quantifying phenotypes of whole slide images

    … explored in this study (i) feature extraction by Resnet50, InceptionV3, VGG16 and an unsupervised generative model, PathologyGAN. (ii) feature space transformer including original feature, 3D PCA feature and 3D-UMAP feature and (iii) clustering algorithms namely Gaussian Mixture Model and …

    glasgow Repository record for An analytical framework of tissue-patch clustering for quantifying phenotypes of whole slide images (opens in a new tab) Download PDF for An analytical framework of tissue-patch clustering for quantifying phenotypes of whole slide images (opens in a new tab)

  17. Brain Tumor Detection Using MRI Images

    … achieve an accuracy of 96.0% for VGG-16, 94% for Resnet50, and 90.7% for the InceptionV3 model. In order to improve the accuracy even further, Bayesian Optimization is leveraged as a hyperparameter tuning technique to obtain the best set of parameters. We could achieve the accuracy of 97.5% for …

    csusb Repository record for Brain Tumor Detection Using MRI Images (opens in a new tab)

  18. Impact of Training Data Volume on Neural Network Training and Accuracy

    … networks performing classification tasks, namely ResNet50 and MobileNetV2. The objective is to investigate the behaviour and accuracy of these networks as they are trained on progressively smaller subsets of the original dataset. With this study, we aim to gain some insight into how neural …

    chalmers Repository record for Impact of Training Data Volume on Neural Network Training and Accuracy (opens in a new tab)

  19. Detekce povrchových defektů kovových dílů pomocí neuronových sítí

    … byla naměřena jako nejpřesnější architektura ResNet50 s průměrnou přesností 88,64 a 61,10 AUROC. Podle naměřených hodnot je množina MPDD2 nejtěžší pro detekci anomálií.

    brno-tech Repository record for Detekce povrchových defektů kovových dílů pomocí neuronových sítí (opens in a new tab)

Page 1 of 7