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"”.
-
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 …
-
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 …
-
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 …
-
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 …
-
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% …
-
Hluboké neuronové sítě v rozpoznávání obrazu
… jejich výsledky pomocí experimentů na datasetu Cifar-10. Konkrétně RMSPROP a normalizovaný SGD
-
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 …
-
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 …
-
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 …
-
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 …
-
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.
-
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 …
-
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++.
-
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 …
-
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 …
-
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 …
-
Piecewise Diffusive Score-based Generative Model
… various toy datasets and a small subset of CIFAR-10.
-
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 …
-
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 …
-
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 …
Page 1 of 11