diff --git a/src/Bmlj/Clustering_mlj.jl b/src/Bmlj/Clustering_mlj.jl
index bca2e604..ae4ac525 100644
--- a/src/Bmlj/Clustering_mlj.jl
+++ b/src/Bmlj/Clustering_mlj.jl
@@ -209,7 +209,10 @@ end
 # Model metadata for registration in MLJ...
 
 MMI.metadata_model(KMeansClusterer,
-    input_scitype    = MMI.Table(MMI.Continuous),         # scitype of the inputs
+    input_scitype = Union{                                # scitype of the inputs
+        MMI.Table(MMI.Continuous),
+        AbstractMatrix{<: MMI.Continuous},
+    },      
     output_scitype   = MMI.Table(MMI.Continuous),         # scitype of the output of `transform`
     target_scitype   = AbstractArray{<:MMI.Multiclass},   # scitype of the output of `predict`
     supports_weights = false,                             # does the model support sample weights?
@@ -217,7 +220,10 @@ MMI.metadata_model(KMeansClusterer,
 )
 
 MMI.metadata_model(KMedoidsClusterer,
-    input_scitype    = MMI.Table(MMI.Continuous),         # scitype of the inputs
+    input_scitype = Union{                                # scitype of the inputs
+        MMI.Table(MMI.Continuous),
+        AbstractMatrix{<: MMI.Continuous},
+    },
     output_scitype   = MMI.Table(MMI.Continuous),         # scitype of the output of `transform`
     target_scitype   = AbstractArray{<:MMI.Multiclass},   # scitype of the output of `predict`
     supports_weights = false,                             # does the model support sample weights?
diff --git a/src/Bmlj/GMM_mlj.jl b/src/Bmlj/GMM_mlj.jl
index 2eea2f78..1c0a1bdd 100644
--- a/src/Bmlj/GMM_mlj.jl
+++ b/src/Bmlj/GMM_mlj.jl
@@ -426,7 +426,10 @@ end
 # Model metadata for registration in MLJ...
 
 MMI.metadata_model(GaussianMixtureClusterer,
-    input_scitype    = MMI.Table(Union{MMI.Continuous,MMI.Missing}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Continuous,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Continuous,MMI.Missing}},
+    },
     output_scitype   = AbstractArray{<:MMI.Multiclass},       # scitype of the output of `transform`
     target_scitype   = AbstractArray{<:MMI.Multiclass},       # scitype of the output of `predict`
     #prediction_type  = :probabilistic,  # option not added to metadata_model function, need to do it separately
@@ -436,13 +439,19 @@ MMI.metadata_model(GaussianMixtureClusterer,
 MMI.prediction_type(::Type{<:GaussianMixtureClusterer}) = :probabilistic
 
 MMI.metadata_model(GaussianMixtureRegressor,
-    input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Infinite}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Infinite,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Infinite,MMI.Missing}},
+    },
     target_scitype   = AbstractVector{<: MMI.Continuous},           # for a supervised model, what target?
     supports_weights = false,                                       # does the model support sample weights?
 	load_path        = "BetaML.Bmlj.GaussianMixtureRegressor"
 )
 MMI.metadata_model(MultitargetGaussianMixtureRegressor,
-    input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Infinite}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Infinite,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Infinite,MMI.Missing}},
+    },
     target_scitype   = AbstractMatrix{<: MMI.Continuous},           # for a supervised model, what target?
     supports_weights = false,                                       # does the model support sample weights?
 	load_path        = "BetaML.Bmlj.MultitargetGaussianMixtureRegressor"
diff --git a/src/Bmlj/Imputation_mlj.jl b/src/Bmlj/Imputation_mlj.jl
index 4cd1b366..3279eecd 100644
--- a/src/Bmlj/Imputation_mlj.jl
+++ b/src/Bmlj/Imputation_mlj.jl
@@ -482,27 +482,39 @@ end
 # Model metadata for registration in MLJ...
 
 MMI.metadata_model(SimpleImputer,
-    input_scitype    = MMI.Table(Union{MMI.Continuous,MMI.Missing}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Continuous,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Continuous,MMI.Missing}},
+    },
     output_scitype   = MMI.Table(MMI.Continuous),     # for an unsupervised, what output?
     supports_weights = false,                         # does the model support sample weights?
 	load_path        = "BetaML.Bmlj.SimpleImputer"
 )
 
 MMI.metadata_model(GaussianMixtureImputer,
-    input_scitype    = MMI.Table(Union{MMI.Continuous,MMI.Missing}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Continuous,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Continuous,MMI.Missing}},
+    },
     output_scitype   = MMI.Table(MMI.Continuous),     # for an unsupervised, what output?
     supports_weights = false,                         # does the model support sample weights?
 	load_path        = "BetaML.Bmlj.GaussianMixtureImputer"
 )
 
 MMI.metadata_model(RandomForestImputer,
-    input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Known}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Known,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Known,MMI.Missing}},
+    },
     output_scitype   = MMI.Table(MMI.Known),          # for an unsupervised, what output?
     supports_weights = false,                         # does the model support sample weights?
 	load_path        = "BetaML.Bmlj.RandomForestImputer"
 )
 MMI.metadata_model(GeneralImputer,
-    input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Known}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Known,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Known,MMI.Missing}},
+    },
     output_scitype   = MMI.Table(MMI.Known),          # for an unsupervised, what output?
     supports_weights = false,                         # does the model support sample weights?
 	load_path        = "BetaML.Bmlj.GeneralImputer"
diff --git a/src/Bmlj/Nn_mlj.jl b/src/Bmlj/Nn_mlj.jl
index 9a10d6b6..c6a813d4 100644
--- a/src/Bmlj/Nn_mlj.jl
+++ b/src/Bmlj/Nn_mlj.jl
@@ -110,7 +110,10 @@ function MMI.fit(m::NeuralNetworkRegressor, verbosity, X, y)
  MMI.predict(m::NeuralNetworkRegressor, fitresult, Xnew) = BetaML.Api.predict(fitresult, MMI.matrix(Xnew))
 
  MMI.metadata_model(NeuralNetworkRegressor,
-    input_scitype    = MMI.Table(Union{MMI.Continuous,MMI.Count}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Continuous,MMI.Count}),
+        AbstractMatrix{<:Union{MMI.Continuous,MMI.Count}},
+    },
     target_scitype   = AbstractVector{<: Union{MMI.Continuous,MMI.Count}},
     supports_weights = false,
     load_path        = "BetaML.Bmlj.NeuralNetworkRegressor"
@@ -223,7 +226,10 @@ function MMI.fit(m::MultitargetNeuralNetworkRegressor, verbosity, X, y)
  MMI.predict(m::MultitargetNeuralNetworkRegressor, fitresult, Xnew) = BetaML.Api.predict(fitresult, MMI.matrix(Xnew))
 
  MMI.metadata_model(MultitargetNeuralNetworkRegressor,
-    input_scitype    = MMI.Table(Union{MMI.Continuous,MMI.Count}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Continuous,MMI.Count}),
+        AbstractMatrix{<:Union{MMI.Continuous,MMI.Count}},
+    },
     target_scitype   = AbstractMatrix{<: Union{MMI.Continuous,MMI.Count}},
     supports_weights = false,
     load_path        = "BetaML.Bmlj.MultitargetNeuralNetworkRegressor"
@@ -365,7 +371,10 @@ function MMI.predict(m::NeuralNetworkClassifier, fitresult, Xnew)
 end
 
  MMI.metadata_model(NeuralNetworkClassifier,
-    input_scitype    = MMI.Table(Union{MMI.Continuous,MMI.Count}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Continuous,MMI.Count}),
+        AbstractMatrix{<:Union{MMI.Continuous,MMI.Count}},
+    },
     target_scitype = AbstractVector{<: Union{MMI.Multiclass,MMI.Finite,MMI.Count}},
     supports_weights = false,
     load_path        = "BetaML.Bmlj.NeuralNetworkClassifier"
diff --git a/src/Bmlj/Perceptron_mlj.jl b/src/Bmlj/Perceptron_mlj.jl
index 54098411..8c23b047 100644
--- a/src/Bmlj/Perceptron_mlj.jl
+++ b/src/Bmlj/Perceptron_mlj.jl
@@ -304,21 +304,30 @@ end
 # Model metadata for registration in MLJ...
 
 MMI.metadata_model(PerceptronClassifier,
-    input_scitype    = MMI.Table(MMI.Infinite),
+    input_scitype = Union{
+        MMI.Table(MMI.Infinite),
+        AbstractMatrix{<: MMI.Infinite},
+    },
     target_scitype   = AbstractVector{<: MMI.Finite},
     supports_weights = false,
 	load_path        = "BetaML.Bmlj.PerceptronClassifier"
 )
 
 MMI.metadata_model(KernelPerceptronClassifier,
-    input_scitype    = MMI.Table(MMI.Infinite),
+    input_scitype = Union{
+        MMI.Table(MMI.Infinite),
+        AbstractMatrix{<: MMI.Infinite},
+    },
     target_scitype   = AbstractVector{<: MMI.Finite},
     supports_weights = false,
 	load_path        = "BetaML.Bmlj.KernelPerceptronClassifier"
 )
 
 MMI.metadata_model(PegasosClassifier,
-    input_scitype    = MMI.Table(MMI.Infinite),
+    input_scitype = Union{
+        MMI.Table(MMI.Infinite),
+        AbstractMatrix{<: MMI.Infinite},
+    },
     target_scitype   = AbstractVector{<: MMI.Finite},
     supports_weights = false,
 	load_path        = "BetaML.Bmlj.PegasosClassifier"
diff --git a/src/Bmlj/Trees_mlj.jl b/src/Bmlj/Trees_mlj.jl
index 9330979f..780a6565 100644
--- a/src/Bmlj/Trees_mlj.jl
+++ b/src/Bmlj/Trees_mlj.jl
@@ -378,25 +378,37 @@ end
 # Model metadata for registration in MLJ...
 
 MMI.metadata_model(DecisionTreeRegressor,
-    input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Known}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Known,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Known,MMI.Missing}},
+    },
     target_scitype   = AbstractVector{<: MMI.Continuous},           # for a supervised model, what target?
     supports_weights = false,                                       # does the model support sample weights?
 	load_path        = "BetaML.Bmlj.DecisionTreeRegressor"
     )
 MMI.metadata_model(RandomForestRegressor,
-    input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Known}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Known,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Known,MMI.Missing}},
+    },
     target_scitype   = AbstractVector{<: MMI.Continuous},
     supports_weights = false,
 	load_path        = "BetaML.Bmlj.RandomForestRegressor"
     )
 MMI.metadata_model(DecisionTreeClassifier,
-    input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Known}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Known,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Known,MMI.Missing}},
+    },
     target_scitype   = AbstractVector{<: Union{MMI.Missing,MMI.Finite}},
     supports_weights = false,
 	load_path        = "BetaML.Bmlj.DecisionTreeClassifier"
     )
 MMI.metadata_model(RandomForestClassifier,
-    input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Known}),
+    input_scitype = Union{
+        MMI.Table(Union{MMI.Known,MMI.Missing}),
+        AbstractMatrix{<:Union{MMI.Known,MMI.Missing}},
+    },
     target_scitype   = AbstractVector{<: Union{MMI.Missing,MMI.Finite}},
     supports_weights = false,
 	load_path        = "BetaML.Bmlj.RandomForestClassifier"
diff --git a/src/Bmlj/Utils_mlj.jl b/src/Bmlj/Utils_mlj.jl
index 03aa11d6..290dd410 100644
--- a/src/Bmlj/Utils_mlj.jl
+++ b/src/Bmlj/Utils_mlj.jl
@@ -157,9 +157,11 @@ function MMI.fit(m::AutoEncoder, verbosity, X)
 
  MMI.inverse_transform(m::AutoEncoder, fitresult, Xnew) = BetaML.Api.inverse_predict(fitresult, MMI.matrix(Xnew))
 
-
  MMI.metadata_model(AutoEncoder,
-    input_scitype    = MMI.Table(Union{MMI.Continuous,MMI.Count}),
+    input_scitype = Union{
+      MMI.Table(Union{MMI.Continuous,MMI.Count}),
+      AbstractMatrix{<:Union{MMI.Continuous,MMI.Count}},
+  },
     output_scitype   = AbstractMatrix{<: Union{MMI.Continuous,MMI.Count}},
     supports_weights = false,
     load_path        = "BetaML.Bmlj.AutoEncoder"