487 datasets found

QuadConv: Quadrature-based convolutions with applications to non-uniform PDE data compression.

The dataset used in the paper is a graph neural network (GNN) dataset, where the goal is to learn a GNN with one hidden layer for node information convolution.

The dataset used in this paper for tracking intracellular protein growth dynamics.

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 paper proposes a decomposition of the convolutional filters over joint steerable bases across the space and the group geometry simultaneously, namely a rotation-equivariant...

The CIC 2020 dataset is a collection of images with different compression methods.

DaCeML is a Data-Centric Machine Learning framework that provides a simple, flexible, and customizable pipeline for optimizing training of arbitrary deep neural networks.

Pathology slides of lung malignancies are classified using resource-frugal convolution neural networks (CNNs) that may be deployed on mobile devices.

A dataset for predicting gene expression from genomic sequence using deep convolutional neural networks.

The dataset used in the paper is a collection of functions that can be represented by a deep network, but cannot be represented by a shallow network.

The dataset used in this paper is a stochastic distributed training dataset for deep neural networks.

The proposed work uses the magnitude and phase of the Fourier Spectrum and the entropy of the image to defend against Adversarial Examples.

Deep convolutional neural networks have recently proven extremely competitive in challenging image recognition tasks. This paper proposes the epitomic convolution as a new...

The dataset used in the paper is a large-scale comparison of pretrained models across computer vision tasks.

Clustering is a fundamental task in data analysis. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, achieves state-of-the-art...

The dataset used for training and testing the proposed method.

The DenseNet dataset is a dataset for image recognition on handwritten digits composed of 60,000 training data and 10,000 test images.

Structural re-parameterization technology provides a new idea to improve the performance of traditional convolutional networks.

The dataset used in this paper is a synthetic dataset of 11940 transmission spectra of exoplanets, generated using the Alfnoor-forward pipeline.

A deep Convolutional Neural Network for topology optimization with strong generalization ability