Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing

Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing

Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high computational time and energy requirements. Also, previously seen t...

Full description

Bibliographic Details
Main Authors: Syed Shakib Sarwar, Aayush Ankit, Kaushik Roy
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Incremental learning
catastrophic forgetting
lifelong learning
energy-efficient learning
network sharing
Online Access:https://ieeexplore.ieee.org/document/8945358/

Internet

https://ieeexplore.ieee.org/document/8945358/

Similar Items