Please use this identifier to cite or link to this item:
|Title:||Dynamically growing neural network architecture for lifelong deep learning on the edge||Authors:||Piyasena, Duvindu
Engineering::Computer science and engineering
|Issue Date:||2020||Source:||Piyasena, D., Thathsara, M., Kanagarajah, S., Lam, S.-K., & Wu, M. (2020). Dynamically growing neural network architecture for lifelong deep learning on the edge. Proceedings of the 2020 30th International Conference on Field-Programmable Logic and Applications (FPL), 262-268. doi:10.1109/FPL50879.2020.00051||Abstract:||Conventional deep learning models are trained once and deployed. However, models deployed in agents operating in dynamic environments need to constantly acquire new knowledge, while preventing catastrophic forgetting of previous knowledge. This ability is commonly referred to as lifelong learning. In this paper, we address the performance and resource challenges for realizing lifelong learning on edge devices. We propose a FPGA based architecture for a Self-Organization Neural Network (SONN), that in combination with a Convolutional Neural Network (CNN) can perform class-incremental lifelong learning for object classification. The proposed SONN architecture is capable of performing unsupervised learning on input features from the CNN by dynamically growing neurons and connections. In order to meet the tight constraints of edge computing, we introduce efficient scheduling methods to maximize resource reuse and parallelism, as well as approximate computing strategies. Experiments based on the Core50 dataset for continuous object recognition from video sequences demonstrated that the proposed FPGA architecture significantly outperforms CPU and GPU based implementations.||URI:||https://hdl.handle.net/10356/146242||ISBN:||9781728199023||DOI:||10.1109/FPL50879.2020.00051||Rights:||© 2020 IEEE. All rights reserved.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||SCSE Conference Papers|
Updated on Apr 23, 2021
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.