Autoencoder class
Superclasses:
Autoencoder class
Description
AnAutoencoder
对象包含一个autoencoder网络,这缺点ists of an encoder and a decoder. The encoder maps the input to a hidden representation. The decoder attempts to map this representation back to the original input.
Construction
returns an autoencoder trained using the training data inautoenc
= trainAutoencoder(X
)X
.
returns an autoencoder with the hidden representation size ofautoenc
= trainAutoencoder(X
,hiddenSize
)hiddenSize
.
returns an autoencoder for any of the above input arguments with additional options specified by one or more name-value pair arguments.autoenc
= trainAutoencoder(___,Name,Value
)
Input Arguments
Properties
Methods
decode | Decode encoded data |
encode | Encode input data |
generateFunction | Generate a MATLAB function to run the autoencoder |
generateSimulink | Generate a万博1manbetxmodel for the autoencoder |
network | ConvertAutoencoder object intonetwork object |
plotWeights | Plot a visualization of the weights for the encoder of an autoencoder |
predict | Reconstruct the inputs using trained autoencoder |
堆栈 | Stack encoders from several autoencoders together |
view | View autoencoder |
Copy Semantics
Value. To learn how value classes affect copy operations, seeCopying Objects.