On a Mechanism Framework of Autoencoders
This provides a foundational interpretation for autoencoders, potentially benefiting researchers in machine learning, but it is incremental as it builds on existing concepts without introducing new methods.
The paper proposes a theoretical framework for understanding autoencoders, focusing on encoder properties like bijective maps and data disentangling, and explains experimental results of various autoencoder types and their advantages over methods like PCA and decision trees.
This paper proposes a theoretical framework on the mechanism of autoencoders. To the encoder part, under the main use of dimensionality reduction, we investigate its two fundamental properties: bijective maps and data disentangling. The general construction methods of an encoder that satisfies either or both of the above two properties are given. The generalization mechanism of autoencoders is modeled. Based on the theoretical framework above, we explain some experimental results of variational autoencoders, denoising autoencoders, and linear-unit autoencoders, with emphasis on the interpretation of the lower-dimensional representation of data via encoders; and the mechanism of image restoration through autoencoders is natural to be understood by those explanations. Compared to PCA and decision trees, the advantages of (generalized) autoencoders on dimensionality reduction and classification are demonstrated, respectively. Convolutional neural networks and randomly weighted neural networks are also interpreted by this framework.