Liquid state machine with dendritically enhanced readout for low-power, neuromorphic VLSI implementations
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...
Saved in:
Main Authors: | Roy, Subhrajit, Banerjee, Amitava, Basu, Arindam |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Article |
Language: | English |
Published: |
2015
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/102407 http://hdl.handle.net/10220/24572 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Hardware efficient, neuromorphic dendritically enhanced readout for liquid state machines
by: Roy, Subhrajit, et al.
Published: (2014) -
VLSI design & implementation for system-on-chip applications
by: Sreya Banerjee.
Published: (2013) -
VLSI implementation of a neuron
by: Yan, Yan
Published: (2011) -
Improved margin multi-class classification using dendritic neurons with morphological learning
by: Hussain, Shaista, et al.
Published: (2015) -
VLSI implementation of Reed Solomon encoder and decoder chip
by: Lau, Luh Chyuan.
Published: (2008)