Asymmetric stacked autoencoder
Angshul Majumdar, Aditay Tripathi · 2017
Traditional stacked autoencoders have an equal number of encoders and decoders. However, while fine-tuned as a deep neural network the decoder portion is detached and never used. This begs the question: ‘do we need equal number of decoders and encoders’? In this study we explore asymmetric autoencoders — unequal number of encoders and decoders. We specifically address two tasks — 1. Classification capacity as deep neural network and 2. Compressibility of stacked autoencoder. For both the problems, our asymmetric autoencoders have several encoders but a single decoders. We find that such autoencoders are more accurate compared to traditional symmetrically stacked autoencoders for classification accuracy and also yield slightly better results on compression problems.