114 datasets found

The Hamiltonian neural network architecture is used to solve DE systems. The Hamiltonian NN is an evolution of previously used unsupervised NNs for finding solutions to DEs that...

The dataset used in the paper is Ising models and UAI-challenge datasets.

ECG dataset for segmentation of Electrocardiograms

A neural routing method for fault-tolerant routing in hypercube networks by avoiding faulty nodes.

The dataset used for gradient adversarial training of neural networks.

The dataset is used to study the computational complexity of learning pushforwards of Gaussians under one-hidden-layer ReLU networks.

This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of...

PROBEN1 is a set of neural network problems and benchmarking rules.

The dataset used in this paper is a collection of quantum graphs, where each graph represents a photon path to detectors, and edges between vertices indicate correlation between...

The dataset is used for analyzing individual neurons in pre-trained models.

The dataset used in the paper is related to neural networks and artificial intelligence.

LumièreNet: a simple, modular, and fully neural network-based architecture that synthesizes high-quality, full-pose headshot lecture videos from instructor's audio narration.

Energy-based out-of-distribution detection.

Enhancing the reliability of out-of-distribution image detection in neural networks.

A baseline for detecting misclassified and out-of-distribution examples in neural networks.

Two-sided matching mechanism using a neural network to model two-sided matching and to explore the design space between strategy-proofness and stability.

The dataset consists of 24 state-of-the-art Google edge neural network models, including CNNs, LSTMs, Transducers, and RCNNs.

The dataset used in the paper is a collection of artistic paintings, used to test the symmetry detection capabilities of the neural network.

The dataset used in the paper is a collection of 2D potentials with known symmetry properties, used to train a neural network to detect symmetries.

Training multiple tasks jointly in one deep network yields reduced latency during inference and better performance over the single-task counterpart by sharing certain layers of...