93 datasets found

The dataset used in the paper Neural 3D Mesh Renderer. The dataset consists of 3D models of objects.

Generative Adversarial Networks (GANs) consist of two networks: a generator G(z) and a discriminator D(x). The discriminator is trying to distinguish real objects from objects...

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

The dataset is used for neural collaborative filtering, which is a type of collaborative filtering that uses neural networks to learn the relationships between users and items.

This dataset is used for density-aware NeRF ensembles.

This dataset is used for few-shot novel view synthesis.

NCFA models used in this paper are a subfamily of the models known as MeDIL causal models, originally introduced in (Markham and Grosse-Wentrup, 2020).

Graph Neural Networks (GNNs) have emerged as powerful tools for learning graph-structured data in various domains.

Graphs are frequently used in various fields of computer science, since they constitute a universal modeling tool which allows the description of structured data.

The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions.

The dataset consists of 979,956 job offers written in Spanish, each belonging to one of the following 23 categories: Sales, Administration, Call Center, Technology, Trades,...

The dataset used in this paper is a synthetic dataset with a nonlinear response, where the response is learned by means of a neural network trained to count numbers in synthetic...

ImageNet-Sketch is used as target dataset for domain adaptation.

SVHN, MNIST, and MNIST-M are used as source datasets for domain adaptation.

CIFAR-10-C, CIFAR-100-C, and ImageNet-C are used as target datasets for corruption robustness evaluation.

Common corruptions and perturbations are used to evaluate the robustness of neural networks.

Benchmarking neural network robustness to common corruptions and perturbations.

Tensor regression networks achieve high compression rate of neural networks while having slight impact on performances. They do so by imposing low tensor rank structure on the...

Deep Neural Networks (DNNs) are universal function approximators providing state-of-the-art solutions on wide range of applications. Common perceptual tasks such as speech...

The dataset used in this paper is a neural network, and the authors used it to test the performance of their lookahead pruning method.