A Variable Memory Length Auto Encoder
- Resource Type
- Conference
- Authors
- Ibunu, Shamahil; Weller, Samuel; Took, Clive Cheong
- Source
- 2021 International Joint Conference on Neural Networks (IJCNN) Neural Networks (IJCNN), 2021 International Joint Conference on. :1-4 Jul, 2021
- Subject
- Bioengineering
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Learning systems
Adaptation models
Solid modeling
Three-dimensional displays
Filtering
Neural networks
Time series analysis
Multi channel least mean square algorithm
auto-encoder
feed forward neural network
fractional memory length
- Language
- ISSN
- 2161-4407
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.