A Variable Memory Length Auto Encoder
Shamahil Ibunu, Samuel Weller, Clive Cheong Took · 2021
Auto-encoders typically require batch learning to be effective. There is a lack of online learning mechanisms for auto-encoders. To address this shortcoming in the literature, we propose an auto-encoder that can not only learn on a sample-by-sample basis without back-propagation but also has a memory to benefit from past learning. The memory can be adapted to fit the current state of the data by varying the memory length of the auto-encoder. Simulation supports our approach, especially when the data is nonstationary.