A Variable Memory Length Auto Encoder. / Mohomad Ibunu, Mohomad; Weller, Samuel; Cheong Took, Clive.

2021. Paper presented at The International Joint Conference on Neural Networks 2021.

Research output: Contribution to conferencePaperpeer-review




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.
Original languageEnglish
Publication statusPublished - Jul 2021
EventThe International Joint Conference on Neural Networks 2021 - Virtual
Duration: 18 Jul 202122 Jul 2021


ConferenceThe International Joint Conference on Neural Networks 2021
Abbreviated titleIJCNN 2021
Internet address
This open access research output is licenced under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.

ID: 42570147