# Layer Spaces

### ActivationLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/ActivationLayerSpace.java)

### AutoEncoderLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/AutoEncoderLayerSpace.java)

Layer space for autoencoder layers

### BatchNormalizationSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/BatchNormalizationSpace.java)

LayerSpace for batch normalization layers

### Bidirectional

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/Bidirectional.java)

Bidirectional layer wrapper. Can be used wrap an existing layer space, in the same way that

### ConvolutionLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/ConvolutionLayerSpace.java)

Layer space for convolutional layers

### DenseLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/DenseLayerSpace.java)

layer hyperparameter configuration space for dense layers (i.e., multi-layer perceptron layers)

### EmbeddingLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/EmbeddingLayerSpace.java)

### GlobalPoolingLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/GlobalPoolingLayerSpace.java)

### GravesBidirectionalLSTMLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/GravesBidirectionalLSTMLayerSpace.java)

Layer space for Bidirectional LSTM layers

### GravesLSTMLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/GravesLSTMLayerSpace.java)

Layer space for LSTM layers

### LSTMLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/LSTMLayerSpace.java)

Layer space for LSTM layers

### OCNNLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/OCNNLayerSpace.java)

Use hiddenLayerSize instead

#### **numHidden**

```
public Builder numHidden(int numHidden) 
```

Use hiddenLayerSize instead

* param numHidden
* return

### OutputLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/OutputLayerSpace.java)

Layer hyperparameter configuration space for output layers

### RnnOutputLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/RnnOutputLayerSpace.java)

Layer hyperparametor configuration space for RnnOutputLayer

### SubsamplingLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/SubsamplingLayerSpace.java)

Layer hyperparameter configuration space for subsampling layers

### VariationalAutoencoderLayerSpace

[\[source\]](https://github.com/eclipse/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/VariationalAutoencoderLayerSpace.java)<br>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://deeplearning4j.konduit.ai/en-1.0.0-beta7/arbiter/layer-spaces.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.