153 datasets found

The dataset is used to test the capability of neural stochastic differential equations to represent nonlinear functions of their initial condition.

Interaction Networks: Using a Reinforcement Learner to train other Machine Learning algorithms

The dataset used in this paper is a synthetic neural data generated using the Arneodo system.

The dataset used to train the DJINN models consists of the randomly sampled values used to generate the absorptivity spectra and emissivity spectra as inputs as well as the...

The dataset used in this paper is a simple neural network with 784 input features, 20 latent space features, and 15680 parameters.

The Neural Latents Benchmark (NLB) is a benchmark for evaluating latent variable models of neural population activity.

Latent factor analysis via dynamical systems (LFADS) is an RNN-based variational sequential autoencoder that achieves state-of-the-art performance in denoising high-dimensional...

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...

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 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.

The dataset used in this paper is a simulated dataset with 200 variables and 50 observations. The variables are generated from a multivariate normal distribution with a...

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

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

Retrieving labels for noisy input patterns.

Self-organization to exponential capacity.

Robust exponential memory in Hopfield networks.

Linear error-correcting codes embedded in associative content-addressable memory networks.