构建深度神经网络

使用 MATLAB^® 代码或以交互方式使用深度网络设计器为序列和表格数据构建网络

通过从头开始定义网络架构，为分类、回归和预测等任务创建新的深度网络。使用 MATLAB 或以交互方式使用深度网络设计器构建网络。

对于大多数任务，您可以使用内置层。如果没有您的任务所需的内置层，则可以定义您自己的自定义层。您可以使用自定义输出层指定自定义损失函数，并定义具有可学习参数和状态参数的自定义层。定义自定义层后，您可以检查该层是否有效，是否与 GPU 兼容，以及是否输出正确定义的梯度。要查看支持的层的列表，请参阅深度学习层列表。

对于层图不支持的模型，您可以将自定义模型定义为函数。要了解详细信息，请参阅定义自定义训练循环、损失函数和网络。

App

深度网络设计器

设计、可视化和训练深度学习网络

函数

全部展开

内置层

输入层

`sequenceInputLayer`	Sequence input layer
`featureInputLayer`	Feature input layer

循环层

`lstmLayer`	Long short-term memory (LSTM) layer for recurrent neural network (RNN)
`bilstmLayer`	Bidirectional long short-term memory (BiLSTM) layer for recurrent neural network (RNN)
`gruLayer`	Gated recurrent unit (GRU) layer for recurrent neural network (RNN)
`lstmProjectedLayer`	Long short-term memory (LSTM) projected layer for recurrent neural network (RNN)

卷积层、注意力层和全连接层

`convolution1dLayer`	1-D convolutional layer
`transposedConv1dLayer`	Transposed 1-D convolution layer
`selfAttentionLayer`	Self-attention layer
`fullyConnectedLayer`	Fully connected layer

激活层和丢弃层

`reluLayer`	修正线性单元 (ReLU) 层
`leakyReluLayer`	Leaky Rectified Linear Unit (ReLU) layer
`clippedReluLayer`	Clipped Rectified Linear Unit (ReLU) layer
`eluLayer`	Exponential linear unit (ELU) layer
`tanhLayer`	双曲正切 (tanh) 层
`swishLayer`	Swish layer
`geluLayer`	Gaussian error linear unit (GELU) layer
`sigmoidLayer`	Sigmoid layer
`softmaxLayer`	Softmax 层
`dropoutLayer`	Dropout layer
`functionLayer`	Function layer

归一化层

`batchNormalizationLayer`	Batch normalization layer
`groupNormalizationLayer`	Group normalization layer
`instanceNormalizationLayer`	Instance normalization layer
`layerNormalizationLayer`	Layer normalization layer
`crossChannelNormalizationLayer`	Channel-wise local response normalization layer

池化层

`maxPooling1dLayer`	1-D max pooling layer
`averagePooling1dLayer`	1-D average pooling layer
`globalMaxPooling1dLayer`	1-D global max pooling layer
`globalAveragePooling1dLayer`	1-D global average pooling layer

组合层

`additionLayer`	Addition layer
`multiplicationLayer`	Multiplication layer
`concatenationLayer`	Concatenation layer
`depthConcatenationLayer`	Depth concatenation layer

数据操作

`sequenceFoldingLayer`	Sequence folding layer
`sequenceUnfoldingLayer`	Sequence unfolding layer
`flattenLayer`	Flatten layer

输出层

`classificationLayer`	分类输出层
`regressionLayer`	回归输出层

构建网络

`layerGraph`	Graph of network layers for deep learning
`plot`	Plot neural network architecture
`addLayers`	Add layers to layer graph or network
`removeLayers`	Remove layers from layer graph or network
`replaceLayer`	Replace layer in layer graph or network
`connectLayers`	Connect layers in layer graph or network
`disconnectLayers`	Disconnect layers in layer graph or network
`DAGNetwork`	Directed acyclic graph (DAG) network for deep learning
`isequal`	Check equality of deep learning layer graphs or networks
`isequaln`	Check equality of deep learning layer graphs or networks ignoring `NaN` values
`analyzeNetwork`	Analyze deep learning network architecture

自定义网络

`dlnetwork`	Deep learning network for custom training loops
`addInputLayer`	Add input layer to network
`summary`	Print network summary
`initialize`	Initialize learnable and state parameters of a `dlnetwork`
`networkDataLayout`	Deep learning network data layout for learnable parameter initialization
`checkLayer`	Check validity of custom or function layer

主题

内置层

Train Network with Numeric Features
This example shows how to create and train a simple neural network for deep learning feature data classification.
使用深度网络设计器创建简单的序列分类网络
此示例说明如何使用深度网络设计器创建简单的长短期记忆 (LSTM) 分类网络。
使用深度学习进行序列分类
此示例说明如何使用长短期记忆 (LSTM) 网络对序列数据进行分类。
使用深度学习进行“序列到序列”分类
此示例说明如何使用长短期记忆 (LSTM) 网络对序列数据的每个时间步进行分类。
使用深度学习进行“序列到序列”回归
此示例说明如何使用深度学习预测发动机的剩余使用寿命 (RUL)。
Sequence-to-One Regression Using Deep Learning
This example shows how to predict the frequency of a waveform using a long short-term memory (LSTM) neural network.
长短期记忆神经网络
了解长短期记忆 (LSTM) 神经网络。
Example Deep Learning Networks Architectures
This example shows how to define simple deep learning neural networks for classification and regression tasks.
Multiple-Input and Multiple-Output Networks
Learn how to define and train deep learning networks with multiple inputs or multiple outputs.
深度学习层列表
探索 MATLAB 中的所有深度学习层。
使用深度网络设计器构建网络
在深度网络设计器中以交互方式构建和编辑深度学习网络。
在 MATLAB 中进行深度学习
通过使用卷积神经网络进行分类和回归来探索 MATLAB 的深度学习能力，包括预训练网络和迁移学习，以及在 GPU、CPU、集群和云上进行训练。
Deep Learning Tips and Tricks
Learn how to improve the accuracy of deep learning networks.
Data Sets for Deep Learning
Discover data sets for various deep learning tasks.

自定义层

定义自定义深度学习层
了解如何定义自定义深度学习层。
Define Custom Deep Learning Intermediate Layers
Learn how to define custom deep learning intermediate layers.
Define Custom Deep Learning Output Layers
Learn how to define custom deep learning output layers.
Check Custom Layer Validity
Learn how to check the validity of custom deep learning layers.
Replace Unsupported Keras Layer with Function Layer
This example shows how to import the layers from a pretrained Keras network, replace the unsupported layers with function layers, and assemble the layers into a network ready for prediction.