625 datasets found

The MNIST and CIFAR-10 datasets are used to evaluate the proposed min-max optimization strategy on adversarial attack and defense tasks.

The dataset used in the paper is a suite of 16 real benchmarks for deep learning and image processing applications.

A database consisting of about 1500 image data from players from every draft since 1990.

Protein secondary structure prediction using deep supervised and convolutional generative stochastic network

Protein secondary structure prediction using deep inception-inside-inception networks

PAKDD Recobell dataset, Instacart dataset

The proposed end-to-end optimized image compression model using the frequency-oriented transform.

Social media hold valuable, vast and unstructured information on public opinion that can be utilized to improve products and services. The automatic analysis of such data,...

Computational cytometer based on magnetically modulated coherent imaging and deep learning

The authors used Tiny-ImageNet, CIFAR100, and CIFAR10 datasets for their experiments.

A new approach to a value network architecture for the game Go, called a multi-labelled (ML) value network. The ML value network has the three advantages, offering different...

The Malimg dataset consists of malware images that were processed from malware binaries, and then trained the following DL models: CNN-SVM, GRU-SVM, and MLP-SVM.

The proposed method for unsupervised deep learning of handwritten text line segmentation.

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 used in the paper is ResNet-20 and ResNet-SVM-20, two types of convolutional neural networks.

CeBed is a benchmark for deep data-driven OFDM channel estimation.

The proposed method uses Weighted Boxes Fusion (WBF) algorithm to obtain the aggregated annotations with the implicit annotators' agreement as confidence scores. The estimated...

Claims data from two US health systems with a general patient population and diverse payer mixes.

Hyperspectral image deconvolution using Plug-and-Play framework

Typical large-scale recommender systems use deep learning models that are stored on a large amount of DRAM. These models often rely on embeddings, which consume most of the...