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 18 of 18 for “"CIFAR10"”.
-
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 …
-
Enhancing adversarial robustness of deep neural networks
… achieve state-of-the-art adversarial accuracy on CIFAR10. In the realm of pretrain- then-tune models, Hendrycks el al. (2019) demonstrated that adversarially pretraining a model on ImageNet then adversarially tuning on CIFAR10 greatly improves the adversarial robustness of machine learning models. …
-
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 …
-
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.
-
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 …
-
Beneficial Initializations in Over-Parameterized Machine Learning Problems
… training accuracy. We evaluate LLBoost on CIFAR10, ImageNet-32, and ImageNet and also prove that it reduces the generalization error of any interpolating solution with high probability. By extending our analysis of transfer learning in linear regression, we present an approach for transfer …
-
Time Aware Sigmoid Optimization : a new learning rate scheduling method
… SGD. Results obtained on three datasets (MNIST, CIFAR10, and CIFAR100) and with three different architectures (Lenet, VGG, and RESNET) have shown that TASO presents, in fact, an overall better performance than the other evaluated methods.
-
An Empirical and Theoretical Analysis of the Role of Depth in Convolutional Neural Networks
… a variety of classification experiments on CIFAR10 and ImageNet32 using fully-convolutional nets, ResNets and the convolutional neural tangent kernel (CNTK) that test performance is U-shaped and in fact worsens beyond a critical depth. To better understand this phenomenon, we conduct a …
-
Efficient ML Inference via Matrix-Vector Approximations
… across two representative models, AlexNet on CIFAR10 and DistilBERT on AG News, comparing quantization, sparsification, and low-rank approximations. Our analysis spans four perspectives: (1) how different methods trade off ℓ₂ error and compression, (2) how weight statistics and input …
-
The Deep Rendering Model: Bridging Theory and Practice in Deep Learning
… and comparable to state of the art on the CIFAR10 benchmark.
-
An evaluation of the robustness of the natural-adversarial mutual information-based defense and malware classification against adversarial attacks for deep learning
… effectiveness of MI-Craft and NAMID under the CIFAR10 and MalImg datasets.
-
DL-DI: A Deep Learning Framework for Distributed, Incremental Image Classification
… and Convolutional Neural Networks on MNIST, CIFAR10 datasets. The evaluation results have verified that the DL-DIS framework supports distributed incremental Deep Learning while achieving a reasonably high rate of prediction accuracy.
-
Image Compression and Channel Error Correction using Neurally-Inspired Network Models
… with momentum. Static images, drawn from the CIFAR10 dataset, were passed to the input layer of an anatomically realistic retinal model and encoded as arrays of output spike trains arising from separate layers of integrate-and-fire neurons representing ON and OFF retinal ganglion cells. The …
-
Hash code learning for large scale similarity search
… hashing methods on single-label datasets CIFAR10 and MNIST. Our final contribution is an unsupervised graph construction method which binarizes CNN features and allows the use of quick Hamming distance calculations to approximate pairwise similarity. This graph can be used in various …
-
Large-scale Optimization for Robust Multi-Class Prediction and Resource Allocation
… on small class datasets including MNIST and CIFAR10. In the nominal setting, our IP-generated compact codebooks outperform commonly used large codebooks. Furthermore, in the adversarial setting, our IP-generated codebooks achieve non-trivial robustness. This is surprising due to three …
-
Towards Reliable AI via Efficient Verification of Binarized Neural Networks
… convolutional BNNs on the widely used MNIST and CIFAR10 datasets. No previous BNN verifiers can handle these tasks. Compared to previous (potentially incorrect) exact verification of floating point networks of the same architectures on the same tasks, our system verifies BNNs hundreds to …
-
Data quality in the deep learning era: Active semi-supervised learning and text normalization for natural language understanding
… compared on computer vision datasets such as CIFAR10. Here, we perform a systematic exploration of several semi-supervised methods for three sequence labeling tasks and two classification tasks. Additionally, most methods have assumptions that are less suitable to realistic scenarios. For …
-
Continual Learning of Object Classification in the Real World
… the accuracy in the CIL-LT setup on MNIST, CIFAR10, and CIFAR100. From the multimodal perspective, text-prompt-based approaches for continual learning leverage pre-trained text encoders and learnable prompts to encode textual features for sequentially arrived classes over time. A common …