Liquid state machine with dendritically enhanced readout for low-power, neuromorphic VLSI implementations

• Main Authors: Roy, Subhrajit, Banerjee, Amitava, Basu, Arindam
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2015
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Electronic circuits
• Online Access: https://hdl.handle.net/10356/102407; http://hdl.handle.net/10220/24572
• Institution: Nanyang Technological University

In this paper, we describe a new neuro-inspired, hardware-friendly readout stage for the liquid state machine (LSM), a popular model for reservoir computing. Compared to the parallel perceptron architecture trained by the p-delta algorithm, which is the state of the art in terms of performance of re...