Technical Program

Paper Detail

Paper: PS-2B.34
Session: Poster Session 2B
Location: Symphony/Overture
Session Time: Friday, September 7, 19:30 - 21:30
Presentation Time:Friday, September 7, 19:30 - 21:30
Presentation: Poster
Paper Title: Mod-DeepESN: Modular Deep Echo State Network
Manuscript:  Click here to view manuscript
Authors: Zachariah Carmichael, Humza Syed, Stuart Burtner, Dhireesha Kudithipudi, Rochester Institute of Technology, United States
Abstract: Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient at solving small-scale spatio-temporal problems. however, they underperform for complex tasks that are characterized by multi-scale structures. In this research, an intrinsic plasticity-infused modular deep echo state network architecture is proposed to solve complex and multiple timescale temporal tasks. It outperforms state-of-the-art for time series prediction tasks.