SOTAVerified

AutoML

Automated Machine Learning (AutoML) is a general concept which covers diverse techniques for automated model learning including automatic data preprocessing, architecture search, and model selection. Source: Evaluating recommender systems for AI-driven data science (1905.09205)

Source: CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 501–525 of 641 papers

TitleStatusHype
Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation—0
AutoCP: Automated Pipelines for Accurate Prediction Intervals—0
Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDLCode2
Reusing Trained Layers of Convolutional Neural Networks to Shorten Hyperparameters Tuning Time—0
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksCode1
Neural Ensemble Search for Uncertainty Estimation and Dataset ShiftCode1
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?Code1
Is deep learning necessary for simple classification tasks?Code3
Adaptation Strategies for Automated Machine Learning on Evolving DataCode0
Efficient AutoML Pipeline Search with Matrix and Tensor FactorizationCode1
AutoHAS: Efficient Hyperparameter and Architecture Search—0
AutoML Segmentation for 3D Medical Image Data: Contribution to the MSD Challenge 2018Code1
A Robust Experimental Evaluation of Automated Multi-Label Classification MethodsCode0
A New Deep Neural Architecture Search Pipeline for Face Recognition—0
Noisy Differentiable Architecture SearchCode1
Testing the Robustness of AutoML Systems—0
Frugal Optimization for Cost-related HyperparametersCode2
DriveML: An R Package for Driverless Machine LearningCode1
Lite Transformer with Long-Short Range AttentionCode1
MetaPoison: Practical General-purpose Clean-label Data PoisoningCode1
Evolution of Scikit-Learn Pipelines with Dynamic Structured Grammatical EvolutionCode0
Architecture Disentanglement for Deep Neural NetworksCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
Deep-n-Cheap: An Automated Search Framework for Low Complexity Deep LearningCode1
Model-based Asynchronous Hyperparameter and Neural Architecture SearchCode3
Show:102550
← PrevPage 21 of 26Next →
All datasetsChalearn-AutoML-1Breast Cancer Coimbra Data SetOrdinalDatasetWine

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1marc.boulleRank (AutoML5)6.4—Unverified
2reference_mbRank (AutoML5)5.2—Unverified
3postech.mlg_exbrainRank (AutoML5)5.2—Unverified
4abhishek4Rank (AutoML5)4.6—Unverified
5referenceRank (AutoML5)4.4—Unverified
6reference_lsRank (AutoML5)4—Unverified
7djajeticRank (AutoML5)3—Unverified
8aad_freiburgRank (AutoML5)1.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Logistic RegressionAccuracy97.02—Unverified
#ModelMetricClaimedVerifiedStatus
1Zero-shot-BERT-SORT1:1 Accuracy55—Unverified
#ModelMetricClaimedVerifiedStatus
1Logistic Regressionaccuracy98.33—Unverified