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 30 for “"CIFAR-10"”.
-
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 …
-
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 …
-
Neural Network Pruning for ECG Arrhythmia Classification
… methods are implemented and compared on the CIFAR-10 database and an ECG arrhythmia classification task. Each pruning method employs a pruning phase interleaved with a finetuning phase. It is shown that when performing the scale-factor pruning algorithm on ECG, finetuning time can be …
-
Are Particle-Based Methods the Future of Sampling in Joint Energy Models? A Deep Dive into SVGD and SGLD
… in energy-based models. Experiments on the CIFAR-10 dataset demonstrate that SGLD, particularly with Sharpness-Aware Minimization (SAM), outperforms SVGD in classification accuracy. However, SVGD without SAM, despite its lower classification accuracy, exhibits lower calibration error …
-
Deep adaptive anomaly detection using an active learning framework
… the Oracle into the model. Results on the MNIST, CIFAR-10 and Galaxy Zoo datasets show that our algorithm, Ahunt, significantly outperforms other anomaly detection algorithms used on a fixed, static, set of features. Ahunt can therefore overcome a poor choice of features that happen to be …
-
Data Centric Defenses for Privacy Attacks
… offer a better privacy-utility tradeoff on CIFAR-10 for membership inference, they reduce the reconstruction rate to ≤ 1% while reducing the classification accuracy by only 2% against model inversion attacks. This is the first attempt to defend model inversion and membership inference …
-
Entrópia alapú bizonytalanságbecslés hatása öncímkézésen alapuló félig felügyelt képosztályozásban
… küszöbön alapuló szelekció. A vizsgálatok a CIFAR-10, a CIFAR-100 és az SVHN képosztályozási adathalmazokon történnek.
-
Hardware software co-design of machine learning accelerators using univariate functions
… Applying this to an MLP-based vision model on CIFAR-10, we cut the number of operations by 45%–28%, boosting hardware efficiency. We validate PSA with two hardware accelerators while maintaining the same reference accuracy. First, an unrolled streaming design that reduces LUT + DSP usage by 25% …
-
P2P Based Personalized Federated Learning for Collaborative Model Sharing and Inferencing
… the whole FL model. Experiments on the MNIST and CIFAR-10 datasets demonstrate that this P2P strategy generates more precise models than random client communication.
-
Mathematical Connections between Convolutional Neural Networks and the Scattering Transformation
… the scattering transformation on both the CIFAR-10 dataset and a publicly available dataset from TensorFlow (datasets.bee_dataset). Results include similar (though at times decreased) accuracy but improved stability compared to that of two Keras Conv2D and MaxPooling2D layers.
-
Deep learning of visual features with limited supervision.
… we achieve 77% accuracy on imbalanced CIFAR-10 using only 500k pre-training samples—outperforming full ImageNet pre-training. On Penn Action video classification, our contrastive learning model reaches 76% accuracy, significantly surpassing ViViT model. In active learning on aquatic …
-
Image Compression using Sum-Product Networks
An estimated 79 zettabytes (1021 bytes) of data was generated worldwide in 2021 with even more data expected to be produced in the future. The effective storage and communication of such large amounts of data is an important problem. Data compression lies at the heart of the solution to this issue. …
-
TwinDNN: A tale of two deep neural networks
… our design on two image classification tasks: CIFAR-10 and ImageNet. Our experiments show that our design can recover up to 94% of accuracy drop caused by extreme network compression, with more than 90% increase in throughput compared to just using the original DNN. This is more than 17% extra …
-
Multi-model-based defense against adversarial examples for neural networks
… in a white-box attack scenario among MNIST, CIFAR-10, and Tiny ImageNet datasets, while maintaining similar accuracy on legitimate examples. Our general framework can also inspire rich future research to construct a desirable model family achieving higher robustness diversity.
-
Query K-means clustering for crowdsourcing
… synthetic and real datasets, including MNIST and CIFAR $10$.
-
Game of threads: Enabling asynchronous poisoning attacks
… degradation and model biasing attacks on the CIFAR-10 image recognition task using ResNet-style DNNs, attacking an asynchronous training implementation published by PyTorch. We perform a deeper analysis on a LeNet-style DNN. We also perform proof-of-concept experiments to validate our …
-
All Analog CNN Accelerator with RRAMs for Fast Inference
… of transistors. This circuit classifies one Cifar-10 dataset image in 6µs (160k frames/s) with 2.4µJ energy per classification with an accuracy of 85%. It contains 7.5 million MAC units and achieves 5 million MAC/mm².
-
Classification of road side material using convolutional neural network and a proposed implementation of the network through Zedboard Zynq 7000 FPGA
… developed a new CNN based on the pre-trained CIFAR-10 network and has used transfer learning on a new problem to classify road edges. Two network sizes were tested: 32 and 16 Neuron inputs with 239 labeled Google street view images on a single CPU. The result of the training gives 52.8% and …
-
Pruning Convolution Neural Network (SqueezeNet) for Efficient Hardware Deployment
… technique is used to train the SqueezeNet on the CIFAR-10 dataset. Results show that the proposed approach reduces the SqueezeNet model by 72% without a significant drop in the accuracy of the model (optimal pruning efficiency result). Results also show that Pruning based on a combination of …
-
Reducing Global Memory Accesses in DNN Training using Structured Weight Masking
… selection was developed and evaluated on the CIFAR-10 dataset. The study systematically varied block sizes and sparsity ratios, analyzing the impact on classification accuracy, theoretical computational cost (FLOPs), and theoretical memory movement. Results indicate that model accuracy remains …
Page 1 of 2