On training deep neural networks using a streaming approach

• Main Authors: Duda, Piotr, Jaworski, Maciej, Cader, Andrzej, Wang, Lipo
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Deep Learning; Data Streams
• Online Access: https://hdl.handle.net/10356/145351
• Institution: Nanyang Technological University

In recent years, many deep learning methods, allowed for a significant improvement of systems based on artificial intelligence methods. Their effectiveness results from an ability to analyze large labeled datasets. The price for such high accuracy is the long training time, necessary to process such...