System Self-Awareness Towards Deep Learning and Discovering High-Value Information

Ying Zhao, Charles Zhou

Abstract

In this paper, we show a System Self-Awareness concept and theory that can be used to discover authoritative and popular information as well as emerging and anomalous information when traditional connections among information nodes (e.g., hyperlinks or citations) are not available. The different categories of information can be all high-value depending on the application requirements. A system self-Awareness is a data-driven concept to discover the uniqueness and innovative capability of a system, modeled and measured using a recursive distributed infrastructure named Collaborative Learning Agents and a deep learning method named Lexical Link Analysis. The combination of the three allows deep reinforcement learning and swarm intelligence to be extended and enhanced in a completely new perspective.

Download


Paper Citation


in Harvard Style

Zhao Y. and Zhou C. (2015). System Self-Awareness Towards Deep Learning and Discovering High-Value Information.In European Projects in Knowledge Applications and Intelligent Systems - Volume 1: EPS Lisbon 2016, ISBN 978-989-758-356-8, pages 160-179. DOI: 10.5220/0007901401600179


in Bibtex Style

@conference{eps lisbon 201615,
author={Ying Zhao and Charles Zhou},
title={System Self-Awareness Towards Deep Learning and Discovering High-Value Information},
booktitle={European Projects in Knowledge Applications and Intelligent Systems - Volume 1: EPS Lisbon 2016,},
year={2015},
pages={160-179},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007901401600179},
isbn={978-989-758-356-8},
}


in EndNote Style

TY - CONF

JO - European Projects in Knowledge Applications and Intelligent Systems - Volume 1: EPS Lisbon 2016,
TI - System Self-Awareness Towards Deep Learning and Discovering High-Value Information
SN - 978-989-758-356-8
AU - Zhao Y.
AU - Zhou C.
PY - 2015
SP - 160
EP - 179
DO - 10.5220/0007901401600179