ECHO STATE QUEUEING NETWORKS: A COMBINATION OF RESERVOIR COMPUTING AND RANDOM NEURAL NETWORKS. Issue 4 (17th May 2017)

• Record Type: Journal Article
• Authors: Basterrech, Sebastián; Rubino, Gerardo
• Is Part Of: Probability in the engineering and informational sciences. Volume 31:Issue 4(2017)
• Page Start: 457
• Page End: 476
• Publication Date: 2017-05-17
• Subjects: applied probability, -- queueing theory, -- operations research, -- computational probability; Probabilities -- Periodicals; Engineering -- Statistical methods -- Periodicals; Information science -- Statistical methods -- Periodicals; 519.202462
• DOI: 10.1017/S0269964817000110
• Languages: English
• ISSNs: 0269-9648

Abstract

Abstract : This paper deals with two ideas appeared during the last developing phase in Artificial Intelligence: Reservoir Computing (RC) and Random Neural Networks. Both have been very successful in many applications. We propose a new model belonging to the first class, taking the structure of the second for its dynamics. The new model is called Echo State Queuing Network. The paper positions the model in the global Machine Learning area, and provides examples of its use and performances. We show on largely used benchmarks that it is a very accurate tool, and we illustrate how it compares with standard RC models.