|
An autoencoder, autoassociator or Diabolo network is an artificial neural network used for learning efficient codings.〔Modeling word perception using the Elman network, Liou, C.-Y., Huang, J.-C. and Yang, W.-C., Neurocomputing, Volume 71, 3150–3157 (2008), 〕〔Autoencoder for Words, Liou, C.-Y., Cheng, C.-W., Liou, J.-W., and Liou, D.-R., Neurocomputing, Volume 139, 84–96 (2014), 〕 The aim of an auto-encoder is to learn a compressed, distributed representation (encoding) for a set of data, typically for the purpose of dimensionality reduction. Supervised learning is employed to teach the network to reproduce the provided input data, and accordingly the method made its appearance when the backpropagation method got traction in the supervised training of multi-layer networks.〔See for example the section "The Encoding Problem" in: David E. Rumelhart, Geoffrey E. Hinton, and Ronald J. Williams, "Learning internal representations by error propagation" (1986)〕 ==Overview== Architecturally, the simplest form of the autoencoder is a feedforward, non-recurrent neural net that is very similar to the multilayer perceptron (MLP), with an input layer, an output layer and one or more hidden layers connecting them. The difference with the MLP is that in an autoencoder, the output layer has equally many nodes as the input layer, and instead of training it to predict some target value given inputs , an autoencoder is trained to ''reconstruct'' its own inputs . I.e., the training algorithm can be summarized as :For each input , ::Do a feed-forward pass to compute activations at all hidden layers, then at the output layer to obtain an output ::Measure the deviation of from the input (typically using squared error, i) ::Backpropagate the error through the net and perform weight updates. (This algorithm trains one sample at a time, but batch learning is also possible.) If the hidden layers are narrower (have fewer nodes) than the input/output layers, then the activations of the final hidden layer can be regarded as a compressed representation of the input. All the usual activation functions from MLPs can be used in autoencoders; if linear activations are used, or only a single sigmoid hidden layer, then the optimal solution to an auto-encoder is strongly related to principal component analysis (PCA). When the hidden layers are larger than the input layer, an autoencoder can potentially learn the identity function and become useless; however, experimental results have shown that such autoencoders might still learn useful features in this case.〔 Auto-encoders can also be used to learn overcomplete feature representations of data. They are the precursor to Deep belief networks. 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「autoencoder」の詳細全文を読む スポンサード リンク
|