SOTAVerified

Unsupervised Pre-training

Pre-training a neural network using unsupervised (self-supervised) auxiliary tasks on unlabeled data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–265 of 265 papers

TitleStatusHype
Learning Deep Representations Using Convolutional Auto-encoders with Symmetric Skip ConnectionsCode0
Unsupervised Learning with Truncated Gaussian Graphical Models—0
Post Training in Deep Learning with Last KernelCode0
Adversarial Ladder Networks—0
What is the Best Feature Learning Procedure in Hierarchical Recognition Architectures?—0
Learning Discriminative Features with Class Encoder—0
Faster learning of deep stacked autoencoders on multi-core systems using synchronized layer-wise pre-training—0
Unsupervised Deep Feature Extraction for Remote Sensing Image Classification—0
Data-dependent Initializations of Convolutional Neural NetworksCode0
How far can we go without convolution: Improving fully-connected networksCode0
Convergence of gradient based pre-training in Denoising autoencoders—0
An Analysis of Unsupervised Pre-training in Light of Recent AdvancesCode0
Learning Non-Linear Reconstruction Models for Image Set Classification—0
Temporal Autoencoding Improves Generative Models of Time Series—0
Knowledge Matters: Importance of Prior Information for OptimizationCode0
Show:102550
← PrevPage 6 of 6Next →
All datasetsMeaslesUCI measles

Benchmark Results

#ModelMetricClaimedVerifiedStatus
115RDLsAccuracy (%)95—Unverified
29RDLsAccuracy (%)94—Unverified
33 RMDLAccuracy (%)93—Unverified
4CNNAccuracy (%)73—Unverified
5RMDLAccuracy (%)0.1—Unverified
#ModelMetricClaimedVerifiedStatus
1RMDL (30 RDLs)Sensitivity (VEB)90.69—Unverified
2Sensitivity89.1—Unverified
3RMDL 3 RDLsSensitivity0.87—Unverified