68 datasets found

The dataset used in this paper is a collection of examples for testing the proposed neural solver for distributed elliptic optimal control problems.

Acoustic vehicle counting using one-channel audio. We predict the pass-by instants of vehicles from local minima of clipped vehicle-to-microphone distance.

ExNN dataset used for credit default prediction

The dataset used in the paper is a discrete-time stochastic dynamical system with two novel aspects: (a) using ranking supermartingales (RSMs) to certify almost-sure asymptotic...

The MNIST and CIFAR datasets are used to test the robustness of neural networks against sparse attacks.

Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns...

The dataset used in this paper is a simulation dataset for retinal prosthetic stimulation optimization. It contains 10,000,000 random stimulus-percept pairs and is used to...

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers...

A neural network architecture for visually-aware recommendation of art images.

Simulated neural networks and larval zebrafish imaging data

The dataset used in this paper is a binary neural network model.

The dataset is used to test the performance of Tangent Bundle Neural Networks on three tasks: denoising of a tangent vector field on the torus, reconstruction from partial...

The dataset used in the paper for neural image compression.

A comprehensive Python framework for evaluating large-scale deep neural networks (DNN) on memristive and memcapacitive crossbar systems, addressing various non-idealities.

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.

DeepLIFT is a method for assigning feature importance that compares a neuron's activation to its'reference', where the reference is the activation that the neuron has when the...

This paper introduces STAR, a framework for spatio-temporal crowd trajectory prediction with only attention mechanisms.

The dataset is used for learning Hamiltonian neural networks.

A dataset of 425,896 unique activation functions, created using the PANGAEA search space.

Three benchmark datasets: Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT, created by training convolutional, residual, and vision transformer architectures from scratch with...