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 54 for “"CIFAR10"”.

  1. Understanding Adversarial Training: Improve Image Recognition Accuracy of Convolution Neural Network

    … types of data sets; MNIST (hand-writing digits), CIFAR10 (animal, food, vehicle pictures), MNIST and CIFAR10 adversarial example. The optimal performance on MNIST and CIFAR10 was achieved by using two essential steps. First, we created a basic convolutional neural network; single layer, defined …

    cuny Repository record for Understanding Adversarial Training: Improve Image Recognition Accuracy of Convolution Neural Network (opens in a new tab)

  2. Konvoliucinių neuroninių tinklų paieška nuotraukoms klasifikuoti /

    … the NAO algorithm performed better using the CIFAR10 dataset with cutouts, auxiliary classificator, and likely with smaller packet sizes and more epochs. However, the CNAS algorithm was superior when using the CIFAR10 dataset with a larger packet size and the Tiny ImageNet dataset. Also, the …

    vilnius Repository record for Konvoliucinių neuroninių tinklų paieška nuotraukoms klasifikuoti / (opens in a new tab)

  3. Application of capsule networks for image classification on complex datasets

    … applying it to complex real world datasets like CIFAR10 and CIFAR100 where the CapsNet’s performance is still unproven. We investigate the operational characteristics of CapsNet for the CIFAR10 problem and identify several practical limitations of Capsules that inhibit their performance in an …

    uiuc Repository record for Application of capsule networks for image classification on complex datasets (opens in a new tab)

  4. Exploratory Analysis of Effects of Data on Adversarial Perturbations

    … the effect of adversarial perturbations on the CIFAR10 image data. Some of these methods involved were mean, standard deviation, variance, covariance, the probability distribution of color channels, etc. This paper discusses the insights found during the analysis of the CIFAR10 image dataset and …

    mississippi Repository record for Exploratory Analysis of Effects of Data on Adversarial Perturbations (opens in a new tab)

  5. FiberNet: um modelo de rede neural convolucional simples e eficiente

    … was evaluated on two datasets, Sisal and CIFAR10. On the Sisal dataset, FiberNet achieved a precision of 96.25%. On the CIFAR10 dataset, FiberNet achieved a precision of 74.9%. Our results show that the Defiber layer is a viable alternative for building low-cost CNNs. Its application in …

    brazil-ufrn Repository record for FiberNet: um modelo de rede neural convolucional simples e eficiente (opens in a new tab)

  6. Evoluční algoritmy v návrhu konvolučních neuronových sítí

    … klasifikácie obrazu na datasetoch MNIST a CIFAR10. Výsledky ukázali, že neuroevolúcia má potenciál hľadať úspešné a efektívne architektúry konvolučných neurónových sietí.

    brno-tech Repository record for Evoluční algoritmy v návrhu konvolučních neuronových sítí (opens in a new tab)

  7. Performance Comparison of Binarized Neural Network with Convolutional Neural Network

    … of dropout on CNN using datasets like MNIST and CIFAR10. The factors like Dropout rate, Dataset size, Batch Normalization layer, Filter size, and Dropout layer addition has been studied on CNN. But there is a lack of literature in the study of dropout and the various factors in Binarized Neural …

    mtu Repository record for Performance Comparison of Binarized Neural Network with Convolutional Neural Network (opens in a new tab)

  8. An Exploration of Linear Classifiers for Unsupervised Spiking Neural Networks with Event-Driven Data

    … from two event-based image datasets, N-MNIST and CIFAR10-DVS. By performing a grid search of important SNN and classifier hyperparameters, we also explore how to improve classification performance of these architectures. Results show that a softmax regression classifier exhibits modest accuracy …

    portland-state Repository record for An Exploration of Linear Classifiers for Unsupervised Spiking Neural Networks with Event-Driven Data (opens in a new tab)

  9. Model Uncertainty-Aware Differentiable Architecture Search

    … minimal model uncertainty. The experiments on CIFAR10, CIFAR100, SVHN, and ImageNet verify the effectiveness of μDARTS in improving accuracy and reducing uncertainty compared to existing DARTS methods. Moreover, the final architecture obtained from μDARTS shows higher robustness to noise at the …

    gatech Repository record for Model Uncertainty-Aware Differentiable Architecture Search (opens in a new tab)

  10. Duomenų augmentacijos metodų palyginimas objektų klasifikavimo uždaviniui /

    … was proposed by the author) and three datasets: CIFAR10, Tiny ImageNet and the dataset of malignant and benign skin moles. After conducting the experiments, it was observed that geometric transformations, mixing of samples and Faster AutoAugment methods were effective in improving the performance …

    vilnius Repository record for Duomenų augmentacijos metodų palyginimas objektų klasifikavimo uždaviniui / (opens in a new tab)

  11. Utilizing network features to detect erroneous inputs

    … erroneous inputs with an AUROC of 0.973 on CIFAR10, 0.957 on Tiny ImageNet, and 0.941 on ImageNet. I experimentally validate the findings across a diverse range of datasets, domains, and pre-trained models.

    colostate Repository record for Utilizing network features to detect erroneous inputs (opens in a new tab)

  12. Training Binary Deep Neural Networks Using Knowledge Distillation

    … in ResNet were suggested and tested. Test on CIFAR10 showed an 1.5% increase in accuracy when using knowledge distillation and an increase of 1.1% when testing on ImageNet dataset. The results indicate that the suggested knowledge distillation method can improve the accuracy of a binary …

    chalmers Repository record for Training Binary Deep Neural Networks Using Knowledge Distillation (opens in a new tab)

  13. Implicit Mixtures of Experts for Rigorous Interpretable Machine Learning

    … benchmark datasets MNIST10, Fashion-MNIST10 and CIFAR10, provided that there are sufficiently many experts in the mixture. If the experts that make up a mixture are simple models, such as linear functions or decision trees of fixed size, then the complexity of a MoE is readily given by the number …

    anu Repository record for Implicit Mixtures of Experts for Rigorous Interpretable Machine Learning (opens in a new tab)

  14. En jämförande studie av regulariserade neurala nätverk med tillämpning på bildklassificering

    … Dataseten som undersöks är MNIST, MNIST-Fashion, CIFAR10 och ett hudcancer-dataset från ISIC. Två simulerade dataset i 2D användes också för att få en visuell idé om hur regularisering påverkar nätverket. Resultaten visar att regularisering ger bättre generalisering, men också att …

    chalmers Repository record for En jämförande studie av regulariserade neurala nätverk med tillämpning på bildklassificering (opens in a new tab)

  15. Implementation of Deep Feedforward Neural Network with CUDA backend for Efficient and Accurate Natural Image Classification

    … the aim to classify tiny natural images from the CIFAR10 dataset. Having 3.274.634 trainable parameters for gray scale input and 4.259.274, 29.853.002 and 30.955.290 trainable parameters for rgb input, the training procedure utilizes a CUDA backend for efficient parameter optimization. The …

    chalmers Repository record for Implementation of Deep Feedforward Neural Network with CUDA backend for Efficient and Accurate Natural Image Classification (opens in a new tab)

  16. A* ATTACK: A NOVEL PATH-FINDING APPROACH TO ADVERSARIAL EXAMPLES

    … a competitive evaluation of the A* Attack on CIFAR10 and ImageNet, comparing its performance against other leading attacks and defenses.

    nps Repository record for A* ATTACK: A NOVEL PATH-FINDING APPROACH TO ADVERSARIAL EXAMPLES (opens in a new tab)

  17. FEDERATED LEARNING OF BAYESIAN NEURAL NETWORKS

    … results—91% accuracy—for IID partitions of the CIFAR10 dataset through federated learning. When the partitions are non-IID, federated learning through inverse variance aggregation of probabilistic weights does as well as its deterministic counterpart, with roughly 83% accuracy. This shows that …

    nps Repository record for FEDERATED LEARNING OF BAYESIAN NEURAL NETWORKS (opens in a new tab)

  18. Exploring internally dense but externally sparse deep convolutional neural networks

    … competitive performance on benchmark tasks (CIFAR10, CIFAR100, and ImageNet) while keeping the network slim. Moreover, the researchers give out connection contributions by implementing a network damage experiment, which could indicate brief principles for hierarchical deep neural network …

    ubc Repository record for Exploring internally dense but externally sparse deep convolutional neural networks (opens in a new tab) Download PDF for Exploring internally dense but externally sparse deep convolutional neural networks (opens in a new tab)

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

    … encoder decoder based architecture (UNet) on the CIFAR10 and Electron Microscopy Dataset with equal parameter sizes on different sparsity levels. It concludes that with the constraint of fixed parameters, the sparse architecture performs better. A linear regression model has been used for …

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

  20. Self-supervision through Random Segments with Autoregressive Coding (RandSAC)

    … alternatives on a number of datasets (e.g., CIFAR10, CIFAR100, ImageNet). While our pre-training strategy works with vanilla Transformer, we also propose a conceptually simple, but highly effective, addition to the decoder that allows learnable skip-connections to encoder’s feature layers, …

    ubc Repository record for Self-supervision through Random Segments with Autoregressive Coding (RandSAC) (opens in a new tab) Download PDF for Self-supervision through Random Segments with Autoregressive Coding (RandSAC) (opens in a new tab)

Page 1 of 3