Dynamically growing neural network architecture for lifelong deep learning on the edge

• Main Authors: Piyasena, Duvindu, Thathsara, Miyuru, Kanagarajah, Sathursan, Lam,Siew-Kei, Wu, Meiqing
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2021
• Subjects: Embedded System; Engineering::Computer science and engineering; Deep Learning; Lifelong Learning
• Online Access: https://hdl.handle.net/10356/146242
• Institution: Nanyang Technological University

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. I...