OpenML-CC18: mnist_784
Best predictive accuracy per machine-learning flow on the mnist_784 classification task from the OpenML-CC18 suite.
Community results for the mnist_784 classification task from OpenML-CC18, OpenML's curated suite of 72 classification tasks (www.openml.org/t/3573). Each subject is a flow — a specific algorithm or pipeline — shown with the best predictive accuracy recorded for it on this task in OpenML's public evaluation listing, under the task's fixed estimation procedure.
Results
predictive_accuracy per subject over 26 measurements, ranked by average.
| Subject | Avg | Median | Min | Max | P95 | P99 | Count |
|---|---|---|---|---|---|---|---|
| torch.nn.modules.container.Sequential.9bf9509fc1a9ea04(1) | 0.994 | 0.994 | 0.994 | 0.994 | 0.994 | 0.994 | 1 |
| keras.wrappers.scikit_learn.KerasClassifier(InputLayer,Reshape,Conv2D,MaxPooling2D,Conv2D,Conv2D,Conv2D,Concatenate,Activation,Conv2D,Conv2D,Conv2D,Concatenate,Activation,Conv2D,Conv2D,Conv2D,Concate… | 0.9939 | 0.9939 | 0.9939 | 0.9939 | 0.9939 | 0.9939 | 1 |
| keras.wrappers.scikit_learn.KerasClassifier(Reshape,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Conv2D,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Fl… | 0.9938 | 0.9938 | 0.9938 | 0.9938 | 0.9938 | 0.9938 | 1 |
| mxnet.gluon.nn.basic_layers.HybridSequential.75709f3c(1) | 0.9915 | 0.9915 | 0.9915 | 0.9915 | 0.9915 | 0.9915 | 1 |
| torch.nn.modules.container.Sequential.e5f895589155e3c(1) | 0.9914 | 0.9914 | 0.9914 | 0.9914 | 0.9914 | 0.9914 | 1 |
| sklearn.pipeline.Pipeline(clf=keras.wrappers.scikit_learn.KerasClassifier)(1) | 0.991 | 0.991 | 0.991 | 0.991 | 0.991 | 0.991 | 1 |
| scikeras.wrappers.KerasClassifier(1) | 0.9887 | 0.9887 | 0.9887 | 0.9887 | 0.9887 | 0.9887 | 1 |
| keras.wrappers.scikit_learn.KerasClassifier(Reshape,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Conv2D,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Fl… | 0.9853 | 0.9853 | 0.9853 | 0.9853 | 0.9853 | 0.9853 | 1 |
| keras.wrappers.scikit_learn.KerasClassifier(2) | 0.9839 | 0.9839 | 0.9839 | 0.9839 | 0.9839 | 0.9839 | 1 |
| sklearn.pipeline.Pipeline(simpleimputer=sklearn.impute._base.SimpleImputer,histgradientboostingclassifier=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(1) | 0.9838 | 0.9838 | 0.9838 | 0.9838 | 0.9838 | 0.9838 | 1 |
| keras.wrappers.scikit_learn.KerasClassifier(InputLayer,Reshape,Conv2D,MaxPooling2D,Conv2D,Conv2D,Conv2D,Merge,Activation,Conv2D,Conv2D,Conv2D,Merge,Activation,Conv2D,Conv2D,Conv2D,Merge,Activation,Ma… | 0.9826 | 0.9826 | 0.9826 | 0.9826 | 0.9826 | 0.9826 | 1 |
| sklearn.pipeline.Pipeline(columntransformer=sklearn.compose._column_transformer.ColumnTransformer(numeric=sklearn.pipeline.Pipeline(imputer=sklearn.preprocessing.imputation.Imputer,standardscaler=skl… | 0.9825 | 0.9825 | 0.9825 | 0.9825 | 0.9825 | 0.9825 | 1 |
| sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold… | 0.9821 | 0.9821 | 0.9821 | 0.9821 | 0.9821 | 0.9821 | 1 |
| keras.wrappers.scikit_learn.KerasClassifier(InputLayer,Reshape,Conv2D,MaxPooling2D,Conv2D,Conv2D,Conv2D,Merge,Activation,Conv2D,Conv2D,Conv2D,Merge,Activation,Conv2D,Conv2D,Conv2D,Merge,Activation,Ma… | 0.9817 | 0.9817 | 0.9817 | 0.9817 | 0.9817 | 0.9817 | 1 |
| torch.nn.Sequential.bb8de941c9933dd2(1) | 0.9814 | 0.9814 | 0.9814 | 0.9814 | 0.9814 | 0.9814 | 1 |
| keras.engine.sequential.Sequential.36D3EA08BAB37560(1) | 0.9812 | 0.9812 | 0.9812 | 0.9812 | 0.9812 | 0.9812 | 1 |
| sklearn.svm.classes.SVC(32) | 0.9809 | 0.9809 | 0.9809 | 0.9809 | 0.9809 | 0.9809 | 1 |
| torch.nn.modules.container.Sequential.4302e8192bf61705(1) | 0.9808 | 0.9808 | 0.9808 | 0.9808 | 0.9808 | 0.9808 | 1 |
| keras.engine.sequential.Sequential.C95B7C6AC5809092(1) | 0.9804 | 0.9804 | 0.9804 | 0.9804 | 0.9804 | 0.9804 | 1 |
| sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold… | 0.9804 | 0.9804 | 0.9804 | 0.9804 | 0.9804 | 0.9804 | 1 |
| sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,scaling=sklearn.preprocessing.data.StandardScaler,variencethre… | 0.9792 | 0.9792 | 0.9792 | 0.9792 | 0.9792 | 0.9792 | 1 |
| sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,scaling=sklearn.preprocessing.data.StandardScaler,variencethre… | 0.9792 | 0.9792 | 0.9792 | 0.9792 | 0.9792 | 0.9792 | 1 |
| sklearn.model_selection._search_successive_halving.HalvingRandomSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(4) | 0.9785 | 0.9785 | 0.9785 | 0.9785 | 0.9785 | 0.9785 | 1 |
| weka.SMO_RBFKernel(2) | 0.9765 | 0.9765 | 0.9765 | 0.9765 | 0.9765 | 0.9765 | 1 |
| weka.SMO_RBFKernel(3) | 0.9765 | 0.9765 | 0.9765 | 0.9765 | 0.9765 | 0.9765 | 1 |
…and 1 more subject.
Metrics
- predictive_accuracy — recorded on each measurement. Best predictive accuracy this flow achieved on the task: the fraction of test instances classified correctly, from 0 to 1. Higher is better
Subjects (26)
- keras.engine.sequential.Sequential.36D3EA08BAB37560(1)
- keras.engine.sequential.Sequential.C95B7C6AC5809092(1)
- keras.wrappers.scikit_learn.KerasClassifier(2)
- keras.wrappers.scikit_learn.KerasClassifier(InputLayer,Reshape,Conv2D,MaxPooling2D,Conv2D,Conv2D,Conv2D,Concatenate,Activation,Conv2D,Conv2D,Conv2D,Concatenate,Activation,Conv2D,Conv2D,Conv2D,Concate…
- keras.wrappers.scikit_learn.KerasClassifier(InputLayer,Reshape,Conv2D,MaxPooling2D,Conv2D,Conv2D,Conv2D,Merge,Activation,Conv2D,Conv2D,Conv2D,Merge,Activation,Conv2D,Conv2D,Conv2D,Merge,Activation,Ma…
- keras.wrappers.scikit_learn.KerasClassifier(InputLayer,Reshape,Conv2D,MaxPooling2D,Conv2D,Conv2D,Conv2D,Merge,Activation,Conv2D,Conv2D,Conv2D,Merge,Activation,Conv2D,Conv2D,Conv2D,Merge,Activation,Ma…
- keras.wrappers.scikit_learn.KerasClassifier(Reshape,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Conv2D,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Fl…
- keras.wrappers.scikit_learn.KerasClassifier(Reshape,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Conv2D,Conv2D,Conv2D,MaxPooling2D,BatchNormalization,Fl…
- keras.wrappers.scikit_learn.KerasClassifier(Reshape,Conv2D,MaxPooling2D,Activation,Conv2D,MaxPooling2D,Activation,Dropout,Conv2D,Flatten,Dense,Activation,Dense,Activation)(5)
- mxnet.gluon.nn.basic_layers.HybridSequential.75709f3c(1)
- scikeras.wrappers.KerasClassifier(1)
- sklearn.model_selection._search_successive_halving.HalvingRandomSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(4)
- sklearn.pipeline.Pipeline(clf=keras.wrappers.scikit_learn.KerasClassifier)(1)
- sklearn.pipeline.Pipeline(columntransformer=sklearn.compose._column_transformer.ColumnTransformer(numeric=sklearn.pipeline.Pipeline(imputer=sklearn.preprocessing.imputation.Imputer,standardscaler=skl…
- sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold…
- sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold…
- sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,scaling=sklearn.preprocessing.data.StandardScaler,variencethre…
- sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,scaling=sklearn.preprocessing.data.StandardScaler,variencethre…
- sklearn.pipeline.Pipeline(simpleimputer=sklearn.impute._base.SimpleImputer,histgradientboostingclassifier=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(1)
- sklearn.svm.classes.SVC(32)
- torch.nn.modules.container.Sequential.4302e8192bf61705(1)
- torch.nn.modules.container.Sequential.9bf9509fc1a9ea04(1)
- torch.nn.modules.container.Sequential.e5f895589155e3c(1)
- torch.nn.Sequential.bb8de941c9933dd2(1)
- weka.SMO_RBFKernel(2)
- weka.SMO_RBFKernel(3)
Published by OpenML.
No observations in this window.