Analysis of Liquid Ensembles for Enhancing the Performance and Accuracy of Liquid State Machines
Liquid state machine (LSM), a bio-inspired computing model consisting of the input sparsely connected to a randomly interlinked reservoir (or liquid) of spiking neurons followed by a readout layer, finds utility in a range of applications varying from robot control and sequence generation to action,...
Main Authors: | Parami Wijesinghe, Gopalakrishnan Srinivasan, Priyadarshini Panda, Kaushik Roy |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2019-05-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2019.00504/full |
Similar Items
-
SpiLinC: Spiking Liquid-Ensemble Computing for Unsupervised Speech and Image Recognition
by: Gopalakrishnan Srinivasan, et al.
Published: (2018-08-01) -
Biologically Plausible Class Discrimination Based Recurrent Neural Network Training for Motor Pattern Generation
by: Parami Wijesinghe, et al.
Published: (2020-08-01) -
Reinforcement Learning With Low-Complexity Liquid State Machines
by: Wachirawit Ponghiran, et al.
Published: (2019-08-01) -
Evidence of amorphous/liquid phase separation in Pd₄₁.₂₅Ni₄₁.₂₅P₁₇.₅ alloy.
Published: (2011) -
Training Deep Spiking Convolutional Neural Networks With STDP-Based Unsupervised Pre-training Followed by Supervised Fine-Tuning
by: Chankyu Lee, et al.
Published: (2018-08-01)