SeNA-CNN: Overcoming Catastrophic Forgetting in Convolutional Neural Networks by Selective Network Augmentation

Lifelong learning aims to develop machine learning systems that can learn new tasks while preserving the performance on previous learned tasks. In this paper we present a method to overcome catastrophic forgetting on convolutional neural networks, that learns new tasks and preserves the performance...

Full description

Bibliographic Details
Main Author: Zacarias, Abel (author)
Other Authors: Alexandre, Luís (author)
Format: conferenceObject
Language:eng
Published: 2020
Subjects:
Lifelong Learning
Catastrophic Forgetting
Convolutional Neural Networks
Supervised Learning
Online Access:http://hdl.handle.net/10400.6/8143
Country:Portugal
Oai:oai:ubibliorum.ubi.pt:10400.6/8143

Internet

http://hdl.handle.net/10400.6/8143

Similar Items