Deep stacked stochastic configuration networks for lifelong learning of non-stationary data streams

• Main Authors: Pratama, Mahardhika, Wang, Dianhui
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Computer science and engineering; Stochastic Configuration Networks; Deep Learning
• Online Access: https://hdl.handle.net/10356/151224
• Institution: Nanyang Technological University

The concept of SCN offers a fast framework with universal approximation guarantee for lifelong learning of non-stationary data streams. Its adaptive scope selection property enables for proper random generation of hidden unit parameters advancing conventional randomized approaches constrained with a...