15 datasets found

A dataset for estimating measurements received over a network, using a deep neural network based approximation architecture.

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using stochastic gradient...

ILMPQ: An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA

The dataset used in this paper is a pre-trained DNN trained on the Cifar10 and Cifar100 datasets.

The dataset used for training deep neural networks using half-precision floating point numbers.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used various neural networks, including AlexNet, VGG16, InceptionV4, ResNet50,...

The dataset used in this paper is a collection of 25 state-of-the-art deep neural networks (DNNs) with different architectures and sizes.

The proposed method uses the MNIST and CIFAR10 datasets for fully-connected DNNs.

The proposed attack is based on transfer-based and score-based methods and is both gradient-free and query-efficient.

The dataset used in the paper to evaluate the alignment of deep neural networks with human perception.

CirCNN is a neural network architecture that uses block-circulant matrices to reduce the number of parameters and computations.

Unitary group convolutions (UGConvs) are a building block for neural networks that combines a group convolution with unitary transforms in feature space.

The VGG-16 and ResNet-50 DNNs are used as victim DNNs in the attack.

The VGG and ResNet DNNs are used as victim DNNs in the attack.

The dataset used in this paper is a MobileNetV2 model, which is a type of deep neural network. The dataset is used to evaluate the performance of the proposed heterogeneous system.