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 207 for “"CIFAR-10"”.

  1. Exploring the Vulnerability of A Neural Tangent Generalization Attack (NTGA) - Generated Unlearnable CIFAR-10 Dataset

    … vulnerability of an NTGA-generated unlearnable CIFAR-10 dataset. Specifically, we show that by employing data augmentation, we can still train a model using the CIFAR-10 dataset generated by NTGA in a centralized learning environment. That is, we experimentally prove that the NTGA-generated …

    usf Repository record for Exploring the Vulnerability of A Neural Tangent Generalization Attack (NTGA) - Generated Unlearnable CIFAR-10 Dataset (opens in a new tab)

  2. Hluboké neuronové sítě v rozpoznávání obrazu

    … pro klasifikaci obrazků na datasetech Caltech101 a Cifar-10. Na příkladu této aplikace diskutuje a měří efektivnost různých technik používaných v CNNs. Výsledky ukazují, že tyto sítě jsou bez dalších rozšíření schopné dosáhnout 80\% přesnosti na datasetu Cifar-10 a 37\% přesnosti na datasetu …

    brno-tech Repository record for Hluboké neuronové sítě v rozpoznávání obrazu (opens in a new tab)

  3. Soft labels and supervised image classification

    … we extend an existing popular image dataset: CIFAR-10. CIFAR- 10 has disjoint, well-defined, and exhaustive labels with 10 classes. We design and execute a survey and graphical user interface to collect individual soft labels for 10,000 images. In the survey, the participants are shown one …

    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)

  4. Analysis of Model Aggregation Techniques in Federated Learning

    … fingerprints, breast cancer dataset, and CIFAR-10 dataset. The proposed aggregation techniques achieved an average of 99.46% model accuracy for handwritten-digits, 82.98% model accuracy for fingerprints, 66.66% mode accuracy for breast cancer, and 60.91% model accuracy for CIFAR-10 …

    regina Repository record for Analysis of Model Aggregation Techniques in Federated Learning (opens in a new tab) Download PDF for Analysis of Model Aggregation Techniques in Federated Learning (opens in a new tab)

  5. Preventing topological collapse in one-shot architecture search via Forman-Ricci curvature

    … on Vision Transformers (ViT, DeiT) across CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that our generated subnets establish a superior Pareto frontier. Our approach strictly dominates standard baselines, achieving up to 7.51% improvement in accuracy on CIFAR-100 and up to 43.3% …

    iastate Repository record for Preventing topological collapse in one-shot architecture search via Forman-Ricci curvature (opens in a new tab)

  6. Hluboké neuronové sítě v rozpoznávání obrazu

    … jejich výsledky pomocí experimentů na datasetu Cifar-10. Konkrétně RMSPROP a normalizovaný SGD

    brno-tech Repository record for Hluboké neuronové sítě v rozpoznávání obrazu (opens in a new tab)

  7. Optimizing Capsule Networks

    … datasets i.e. MNIST, F-MNIST, SVHN and CIFAR-10. QCN however loses testing accuracy marginally compared to the baseline e.g. 1% for F-MNIST dataset. Our second contribution is designing a capsule-specific layer for the feature extractor of CapsNet referred to as the Convolutional …

    uvic Repository record for Optimizing Capsule Networks (opens in a new tab)

  8. Resource and data optimization for hardware implementation of deep neural networks targeting FPGA-based edge devices

    … and 653.5 μs for classifying one image in the Cifar-10 data set using the CifarNet. For the LeNet we were able to maintain high accuracy of 97.6% for the MNIST data set and 83.4% for the Cifar-10 data set. We achieved the best single-image latency, 5.2x faster for the LeNet and 1.95x faster for …

    uiuc Repository record for Resource and data optimization for hardware implementation of deep neural networks targeting FPGA-based edge devices (opens in a new tab)

  9. An Analysis of Heterogeneous Quantization Schemes for Neural Networks

    … perceptron (MLP)—were studied with the MNIST and CIFAR-10 image classification datasets. The weights of the models were quantized during training using the deterministic rounding technique. The models were either quantized homogeneously, with all weights quantized to the same precision, or …

    rit Repository record for An Analysis of Heterogeneous Quantization Schemes for Neural Networks (opens in a new tab)

  10. Automated deep learning architecture design using differentiable architecture search (DARTS)

    … often attained state-of-the-art performances on CIFAR-10, ImageNet and Penn Tree Bank datasets. Even though the search time has been reduced to tens of GPU hours from tens of thousands of GPU hours, most search algorithms rely on additional controllers and hypernetworks to generate architecture …

    colostate Repository record for Automated deep learning architecture design using differentiable architecture search (DARTS) (opens in a new tab)

  11. Small-Scale Dual Path Network for Image Classification and Machine Learning Applications to Color Quantization

    … network for image classifiaction utilizing the CIFAR-10 dataset containing 60,000 32x32 pixel images ranging across ten categories.

    unt Repository record for Small-Scale Dual Path Network for Image Classification and Machine Learning Applications to Color Quantization (opens in a new tab)

  12. DATA SUBSAMPLING FOR MODEL SELECTION IN AUTOML FRAMEWORKS

    … called iterative boosting. The first method uses 10 tabular datasets while the following two approaches use MNIST and CIFAR-10 image datasets and deep learning models. Each of these approaches uses a unique set of assumptions which provide some pros and cons for the intended task of model …

    cornell Repository record for DATA SUBSAMPLING FOR MODEL SELECTION IN AUTOML FRAMEWORKS (opens in a new tab)

  13. Optimalizace hlubokých neuronových sítí

    … LeNet-5 pri využití dátových sád MNIST, CIFAR-10 a SVHN. Implementácia a následná optimalizácia neurónových sietí boli prevedené využitím knižnice Tiny-dnn v programovacom jazyku C++.

    brno-tech Repository record for Optimalizace hlubokých neuronových sítí (opens in a new tab)

  14. Exploring FPGA Implementation for Binarized Neural Network Inference

    … PC-BNN is designed for image classification on CIFAR-10 dataset and explores the hardware architecture and optimization of customized CNN topology. The parallel-convolution binarized neural network has two parallel binarized convolution layers which replaces the original single binarized …

    ucf Repository record for Exploring FPGA Implementation for Binarized Neural Network Inference (opens in a new tab)

  15. AI on the Edge with CondenseNeXt: An Efficient Deep Neural Network for Devices with Constrained Computational Resources

    … performed on three benchmarking image datasets: CIFAR-10, CIFAR-100 and ImageNet by deploying the trained weight on to an ARM-based embedded computing platform: NXP BlueBox 2.0, for real-time image classification. The outputs are observed in real-time in RTMaps Remote Studio’s console to verify …

    iupui Repository record for AI on the Edge with CondenseNeXt: An Efficient Deep Neural Network for Devices with Constrained Computational Resources (opens in a new tab)

  16. Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks

    … format for sparse matrix storage. On LeNet-300-100 (MNIST dataset), LeNet-5 (MNIST dataset), AlexNet (CIFAR-10 dataset) and VGG-16 (CIFAR-10 dataset), post-training quantization achieves 7.62x, 10.87x, 6.39x and 12.43x compression, in-training quantization achieves 22.08x, 21.05x, 7.95x and …

    vt Repository record for Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks (opens in a new tab)

  17. Energy Efficient and Accurate In-Memory Computing Accelerators for Machine Learning

    … compute-density and 89.9% inference accuracy on CIFAR-10 dataset. The second design, namely MC2-RAM (Multi-bit Capacitive Convolution SRAM), proposes a novel 8T SRAM cell that achieves multi-bit in-memory computation with full parallelism and high linearity. Post-layout simulation shows 59.7 …

    rice Repository record for Energy Efficient and Accurate In-Memory Computing Accelerators for Machine Learning (opens in a new tab)

  18. Progressive Hierarchical Classification For Multi-Category Image Classification

    … hierarchical classification model applied to the CIFAR-10 dataset, focusing on addressing the limitations of existing methods, which often struggle with (i) overlapping features and (ii) poor interpretability of classification decisions. The hierarchical model was implemented to mitigate these …

    york Repository record for Progressive Hierarchical Classification For Multi-Category Image Classification (opens in a new tab)

  19. Deep Learning Optimization and Acceleration

    … neural network acceleration. On two datasets (CIFAR-10 and CIFAR-100), the proposed deep neural network optimization and acceleration frameworks are tested using a variety of Convolutional neural networks (e.g., LeNet-5, VGG-16, GoogLeNet, DenseNet, ResNet). Experimental results are promising …

    unt Repository record for Deep Learning Optimization and Acceleration (opens in a new tab)

Page 1 of 11