Main Content

ClassificationNeuralNetwork Predict

Classify observations using neural network classification model

Since R2021b

expand all in page
  • ClassificationNeuralNetwork Predict Block Icon

Libraries:
Statistics and Machine Learning Toolbox / Classification

Description

The ClassificationNeuralNetwork Predict block classifies observations using a neural network classification object (ClassificationNeuralNetwork or CompactClassificationNeuralNetwork) for multiclass classification.

Import a trained classification object into the block by specifying the name of a workspace variable that contains the object. The input port x receives an observation (predictor data), and the output port label returns a predicted class label for the observation. You can add the optional output port score, which returns predicted class scores or posterior probabilities.

Examples

Predict Class Labels Using ClassificationNeuralNetwork Predict Block

Predict Class Labels Using ClassificationNeuralNetwork Predict Block

Train a neural network classification model, and then use the ClassificationNeuralNetwork Predict block for label prediction.

Ports

Input

expand all

Predictor data, specified as a row or column vector of one observation.

The variables in x must have the same order as the predictor variables that trained the model specified by Select trained machine learning model.

Data Types: single | double | half | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | Boolean | fixed point

Output

expand all

Predicted class label, returned as a scalar. The predicted class is the class that minimizes the expected classification cost. For more details, see the More About section of the predict function reference page.

Data Types: single | double | half | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | Boolean | fixed point | enumerated

Predicted class scores or posterior probabilities, returned as a row vector of size 1-by-k, where k is the number of classes in the neural network model. The classification score Score(i) represents the posterior probability that the observation in x belongs to class i.

To check the order of the classes, use the ClassNames property of the neural network model specified by Select trained machine learning model.

Dependencies

To enable this port, select the check box for Add output port for predicted class scores on the Main tab of the Block Parameters dialog box.

Data Types: single | double | half | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | Boolean | fixed point

Parameters

expand all

Main

Specify the name of a workspace variable that contains a ClassificationNeuralNetwork object or CompactClassificationNeuralNetwork object.

When you train the model by using fitcnet, the following restrictions apply:

  • The predictor data cannot include categorical predictors (logical, categorical, char, string, or cell). If you supply training data in a table, the predictors must be numeric (double or single). Also, you cannot use the CategoricalPredictors name-value argument. To include categorical predictors in a model, preprocess them by using dummyvar before fitting the model.

  • The value of the ScoreTransform name-value argument cannot be 'invlogit' or an anonymous function.

Programmatic Use

Block Parameter: TrainedLearner
Type: workspace variable
Values: ClassificationNeuralNetwork object | CompactClassificationNeuralNetwork object
Default: 'nnetMdl'

Select the check box to include the second output port score in the ClassificationNeuralNetwork Predict block.

Programmatic Use

Block Parameter: ShowOutputScore
Type: character vector
Values: 'off' | 'on'
Default: 'off'

Data Types

Fixed-Point Operational Parameters

Specify the rounding mode for fixed-point operations. For more information, see Rounding Modes (Fixed-Point Designer).

Block parameters always round to the nearest representable value. To control the rounding of a block parameter, enter an expression into the mask field using a MATLAB® rounding function.

Programmatic Use

Block Parameter: RndMeth
Type: character vector
Values: "Ceiling" | "Convergent" | "Floor" | "Nearest" | "Round" | "Simplest" | "Zero"
Default: "Floor"

Specify whether overflows saturate or wrap.

ActionRationaleImpact on OverflowsExample

Select this check box (on).

Your model has possible overflow, and you want explicit saturation protection in the generated code.

Overflows saturate to either the minimum or maximum value that the data type can represent.

The maximum value that the int8 (signed 8-bit integer) data type can represent is 127. Any block operation result greater than this maximum value causes overflow of the 8-bit integer. With the check box selected, the block output saturates at 127. Similarly, the block output saturates at a minimum output value of –128.

Clear this check box (off).

You want to optimize the efficiency of your generated code.

You want to avoid overspecifying how a block handles out-of-range signals. For more information, see Troubleshoot Signal Range Errors (Simulink).

Overflows wrap to the appropriate value that the data type can represent.

The maximum value that the int8 (signed 8-bit integer) data type can represent is 127. Any block operation result greater than this maximum value causes overflow of the 8-bit integer. With the check box cleared, the software interprets the value causing the overflow as int8, which can produce an unintended result. For example, a block result of 130 (binary 1000 0010) expressed as int8 is –126.

Programmatic Use

Block Parameter: SaturateOnIntegerOverflow
Type: character vector
Values: "off" | "on"
Default: "off"

Select this parameter to prevent the fixed-point tools from overriding the data type you specify for the block. For more information, see Use Lock Output Data Type Setting (Fixed-Point Designer).

Programmatic Use

Block Parameter: LockScale
Type: character vector
Values: "off" | "on"
Default: "off"
Data Type

Specify the data type for the label output. The type can be inherited, specified as an enumerated data type, or expressed as a data type object such as Simulink.NumericType.

The supported data types depend on the labels used in the model specified by Select trained machine learning model.

  • If the model uses numeric or logical labels, the supported data types are Inherit: Inherit via back propagation (default), double, single, half, int8, uint8, int16, uint16, int32, uint32, int64, uint64, boolean, fixed point, and a data type object.

  • If the model uses nonnumeric labels, the supported data types are Inherit: auto (default), Enum: <class name>, and a data type object.

When you select an inherited option, the software behaves as follows:

  • Inherit: Inherit via back propagation (default for numeric and logical labels) — Simulink® automatically determines the Label data type of the block during data type propagation (see Data Type Propagation (Simulink)). In this case, the block uses the data type of a downstream block or signal object.

  • Inherit: auto (default for nonnumeric labels) — The block uses an autodefined enumerated data type variable. For example, suppose the workspace variable name specified by Select trained machine learning model is myMdl, and the class labels are class 1 and class 2. Then, the corresponding label values are myMdl_enumLabels.class_1 and myMdl_enumLabels.class_2. The block converts the class labels to valid MATLAB identifiers by using the matlab.lang.makeValidName function.

For more information about data types, see Control Data Types of Signals (Simulink).

Click the Show data type assistant button to display the Data Type Assistant, which helps you set the data type attributes. For more information, see Specify Data Types Using Data Type Assistant (Simulink).

Programmatic Use

Block Parameter: LabelDataTypeStr
Type: character vector
Values: "Inherit: Inherit via back propagation" | "Inherit: auto" | "double" | "single" | "half" | "int8" | "uint8" | "int16" | "uint16" | "int32" | "uint32" | "int64" | "uint64" | "boolean" | "fixdt(1,16,0)" | "fixdt(1,16,2^0,0)" | "Enum: <class name>" | "<data type expression>"
Default: "Inherit: Inherit via back propagation" (for numeric and logical labels) | "Inherit: auto" (for nonnumeric labels)

Specify the lower value of the label output range that Simulink checks.

Simulink uses the minimum value to perform:

Note

The Label data type Minimum parameter does not saturate or clip the actual label output signal. To do so, use the Saturation (Simulink) block instead.

Dependencies

You can specify this parameter only if the model specified by Select trained machine learning model uses numeric labels.

Programmatic Use

Block Parameter: LabelOutMin
Type: character vector
Values: "[]" | scalar
Default: "[]"

Specify the upper value of the label output range that Simulink checks.

Simulink uses the maximum value to perform:

Note

The Label data type Maximum parameter does not saturate or clip the actual label output signal. To do so, use the Saturation (Simulink) block instead.

Dependencies

You can specify this parameter only if the model specified by Select trained machine learning model uses numeric labels.

Programmatic Use

Block Parameter: LabelOutMax
Type: character vector
Values: "[]" | scalar
Default: "[]"

Specify the data type for the score output. The type can be inherited, specified directly, or expressed as a data type object such as Simulink.NumericType.

When you select Inherit: auto, the block uses a rule that inherits a data type.

For more information about data types, see Control Data Types of Signals (Simulink).

Click the Show data type assistant button to display the Data Type Assistant, which helps you set the data type attributes. For more information, see Specify Data Types Using Data Type Assistant (Simulink).

Programmatic Use

Block Parameter: ScoreDataTypeStr
Type: character vector
Values: "Inherit: auto" | "double" | "single" | "half" | "int8" | "uint8" | "int16" | "uint16" | "int32" | "uint32" | "int64" | "uint64" | "boolean" | "fixdt(1,16,0)" | "fixdt(1,16,2^0,0)" | "<data type expression>"
Default: "Inherit: auto"

Specify the lower value of the score output range that Simulink checks.

Simulink uses the minimum value to perform:

Note

The Score data type Minimum parameter does not saturate or clip the actual score output. To do so, use the Saturation (Simulink) block instead.

Programmatic Use

Block Parameter: ScoreOutMin
Type: character vector
Values: "[]" | scalar
Default: "[]"

Specify the upper value of the score output range that Simulink checks.

Simulink uses the maximum value to perform:

Note

The Score data type Maximum parameter does not saturate or clip the actual score output. To do so, use the Saturation (Simulink) block instead.

Programmatic Use

Block Parameter: ScoreOutMax
Type: character vector
Values: "[]" | scalar
Default: "[]"

Specify the data type for the internal untransformed scores. The type can be inherited, specified directly, or expressed as a data type object such as Simulink.NumericType.

When you select Inherit: auto, the block uses a rule that inherits a data type.

For more information about data types, see Control Data Types of Signals (Simulink).

Click the Show data type assistant button to display the Data Type Assistant, which helps you set the data type attributes. For more information, see Specify Data Types Using Data Type Assistant (Simulink).

Dependencies

You can specify this parameter only if the model specified by Select trained machine learning model uses a score transformation other than "none" (default, same as "identity").

  • If the model uses no score transformations ("none" or "identity"), then you can specify the score data type by using Score data type.

  • If the model uses a score transformation other than "none" or "identity", then you can specify the data type of untransformed raw scores by using this parameter. To specify the data type of transformed scores, use Score data type.

You can change the score transformation option by specifying the ScoreTransform name-value argument during training, or by modifying the ScoreTransform property after training.

Programmatic Use

Block Parameter: RawScoreDataTypeStr
Type: character vector
Values: "Inherit: auto" | "double" | "single" | "half" | "int8" | "uint8" | "int16" | "uint16" | "int32" | "uint32" | "int64" | "uint64" | "boolean" | "fixdt(1,16,0)" | "fixdt(1,16,2^0,0)" | "<data type expression>"
Default: "Inherit: auto"

Specify the lower value of the untransformed score range that Simulink checks.

Simulink uses the minimum value to perform:

Note

The Raw score data type Minimum parameter does not saturate or clip the actual untransformed score signal.

Programmatic Use

Block Parameter: RawScoreOutMin
Type: character vector
Values: "[]" | scalar
Default: "[]"

Specify the upper value of the untransformed score range that Simulink checks.

Simulink uses the maximum value to perform:

Note

The Raw score data type Maximum parameter does not saturate or clip the actual untransformed score signal.

Programmatic Use

Block Parameter: RawScoreOutMax
Type: character vector
Values: "[]" | scalar
Default: "[]"

Specify the data type for the output layer. The type can be inherited, specified directly, or expressed as a data type object such as Simulink.NumericType.

When you select Inherit: Inherit via internal rule, the block uses an internal rule to determine the output data type. The internal rule chooses a data type that optimizes numerical accuracy, performance, and generated code size, while taking into account the properties of the embedded target hardware. The software cannot always optimize efficiency and numerical accuracy at the same time.

For more information about data types, see Control Data Types of Signals (Simulink).

Click the Show data type assistant button to display the Data Type Assistant, which helps you set the data type attributes. For more information, see Specify Data Types Using Data Type Assistant (Simulink).

Programmatic Use

Block Parameter: OutputLayerDataTypeStr
Type: character vector
Values: 'Inherit: Inherit via internal rule' | 'double' | 'single' | 'half' | 'int8' | 'uint8' | 'int16' | 'uint16' | 'int32' | 'uint32' | 'int64' | 'uint64' | 'boolean' | 'fixdt(1,16,0)' | 'fixdt(1,16,2^0,0)' | '<data type expression>'
Default: 'Inherit: Inherit via internal rule'

Specify the lower value of the output layer's internal variable range checked by Simulink.

Simulink uses the minimum value to perform:

Note

The Output layer data type Minimum parameter does not saturate or clip the output layer value signal.

Programmatic Use

Block Parameter: OutputLayerOutMin
Type: character vector
Values: '[]' | scalar
Default: '[]'

Specify the upper value of the output layer's internal variable range checked by Simulink.

Simulink uses the maximum value to perform:

Note

The Output layer data type Maximum parameter does not saturate or clip the output layer value signal.

Programmatic Use

Block Parameter: OutputLayerOutMax
Type: character vector
Values: '[]' | scalar
Default: '[]'

Specify the data type for the first layer. The type can be inherited, specified directly, or expressed as a data type object such as Simulink.NumericType.

When you select Inherit: Inherit via internal rule, the block uses an internal rule to determine the data type. The internal rule chooses a data type that optimizes numerical accuracy, performance, and generated code size, while taking into account the properties of the embedded target hardware. The software cannot always optimize efficiency and numerical accuracy at the same time.

For more information about data types, see Control Data Types of Signals (Simulink).

Click the Show data type assistant button to display the Data Type Assistant, which helps you set the data type attributes. For more information, see Specify Data Types Using Data Type Assistant (Simulink).

Tips

A trained neural network can have more than one fully connected layer, excluding the output layer.

  • You can specify the data type for each individual layer for the first 10 layers. Specify the data type Layer n data type for each layer. The data type of the first layer is Layer 1 data type, the data type of the second layer is Layer 2 data type, and so on.

  • You can specify the data type for layers 11 to k, where k is the total number of layers, by using the data type Additional layer(s) data type. The Block Parameter for Additional layer(s) data type is Layer11DataTypeStr.

  • The data types Layer n data type and Additional layer(s) data type can be inherited, specified directly, or expressed as a data type object such as Simulink.NumericType. These data types support the same values as Layer 1 data type.

Programmatic Use

Block Parameter: Layer1DataTypeStr
Type: character vector
Values: 'Inherit: Inherit via internal rule' | 'double' | 'single' | 'half' | 'int8' | 'uint8' | 'int16' | 'uint16' | 'int32' | 'uint32' | 'int64' | 'uint64' | 'boolean' | 'fixdt(1,16,0)' | 'fixdt(1,16,2^0,0)' | '<data type expression>'
Default: 'Inherit: Inherit via internal rule'

Specify the lower value of the first layer's internal variable range checked by Simulink.

Simulink uses the minimum value to perform:

Note

The Layer 1 data type Minimum parameter does not saturate or clip the first layer value signal.

Tips

A trained neural network can have more than one fully connected layer, excluding the output layer.

  • You can specify the lower value of each individual layer's internal variable range checked by Simulink for the first 10 layers. Specify the lower value Layer n minimum for each layer. The minimum value of the first layer is Layer 1 minimum, the minimum value of the second layer is Layer 2 minimum, and so on.

  • You can specify the lower value for layers 11 to k, where k is the total number of layers, by using Additional layer(s) minimum. The Block Parameter for Additional layer(s) minimum is Layer11OutMin.

  • Layer n minimum and Additional layer(s) minimum support the same values as Layer 1 minimum.

Programmatic Use

Block Parameter: Layer1OutMin
Type: character vector
Values: '[]' | scalar
Default: '[]'

Specify the upper value of the first layer's internal variable range checked by Simulink.

Simulink uses the maximum value to perform:

Note

The Layer 1 data type Maximum parameter does not saturate or clip the first layer value signal.

Tips

A trained neural network can have more than one fully connected layer, excluding the output layer.

  • You can specify the upper value of each individual layer's internal variable range checked by Simulink for the first 10 layers. Specify the upper value Layer n maximum for each layer. The maximum value of the first layer is Layer 1 maximum, the maximum value of the second layer is Layer 2 maximum, and so on.

  • You can specify the upper value for layers 11 to k, where k is the total number of layers, by using Additional layer(s) maximum. The Block Parameter for Additional layer(s) maximum is Layer11OutMax.

  • Layer n maximum and Additional layer(s) maximum support the same values as Layer 1 maximum.

Programmatic Use

Block Parameter: Layer1OutMax
Type: character vector
Values: '[]' | scalar
Default: '[]'

Block Characteristics

Data Types

Boolean | double | enumerated | fixed point | half | integer | single

Direct Feedthrough

yes

Multidimensional Signals

no

Variable-Size Signals

no

Zero-Crossing Detection

no

Alternative Functionality

You can use a MATLAB Function block with the predict object function of a neural network classification object (ClassificationNeuralNetwork or CompactClassificationNeuralNetwork). For an example, see Predict Class Labels Using MATLAB Function Block.

When deciding whether to use the ClassificationNeuralNetwork Predict block in the Statistics and Machine Learning Toolbox™ library or a MATLAB Function block with the predict function, consider the following:

  • If you use the Statistics and Machine Learning Toolbox library block, you can use the Fixed-Point Tool (Fixed-Point Designer) to convert a floating-point model to fixed point.

  • Support for variable-size arrays must be enabled for a MATLAB Function block with the predict function.

  • If you use a MATLAB Function block, you can use MATLAB functions for preprocessing or post-processing before or after predictions in the same MATLAB Function block.

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using Simulink® Coder™.

Fixed-Point Conversion
Design and simulate fixed-point systems using Fixed-Point Designer™.

Version History

Introduced in R2021b

See Also

Blocks

Objects

Functions

Topics