Reinforcement Learning With Low-Complexity Liquid State Machines

Reinforcement Learning With Low-Complexity Liquid State Machines

We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very little trainable parameters. Such sparse and randomly interconnected recurrent spiking networks exhibit highly non-linear...

Full description

Bibliographic Details
Main Authors:	Wachirawit Ponghiran, Gopalakrishnan Srinivasan, Kaushik Roy
Format:	Article
Language:	English
Published:	Frontiers Media S.A. 2019-08-01
Series:	Frontiers in Neuroscience
Subjects:	liquid state machine recurrent SNN learning without stable states spiking reinforcement learning Q-learning
Online Access:	https://www.frontiersin.org/article/10.3389/fnins.2019.00883/full

Similar Items

ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing
by: Gopalakrishnan Srinivasan, et al.
Published: (2019-03-01)

Improving Liquid State Machines Through Iterative Refinement of the Reservoir
by: Norton, R David
Published: (2008)

Editorial: Spiking Neural Network Learning, Benchmarking, Programming and Executing
by: Guoqi Li, et al.
Published: (2020-04-01)

Analysis of Liquid Ensembles for Enhancing the Performance and Accuracy of Liquid State Machines
by: Parami Wijesinghe, et al.
Published: (2019-05-01)

A Spike Time-Dependent Online Learning Algorithm Derived From Biological Olfaction
by: Ayon Borthakur, et al.
Published: (2019-06-01)

A bidirectional brain-machine interface featuring a neuromorphic hardware decoder
by: Fabio Boi, et al.
Published: (2016-12-01)

A Retinotopic Spiking Neural Network System for Accurate Recognition of Moving Objects Using NeuCube and Dynamic Vision Sensors
by: Lukas Paulun, et al.
Published: (2018-06-01)

Utilizing negative policy information to accelerate reinforcement learning
by: Irani, Arya John
Published: (2015)

Optimization of Spiking Neural Networks Based on Binary Streamed Rate Coding
by: Ali A. Al-Hamid, et al.
Published: (2020-09-01)

Using a Low-Power Spiking Continuous Time Neuron (SCTN) for Sound Signal Processing
by: Moshe Bensimon, et al.
Published: (2021-02-01)

Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks
by: Brian Gardner, et al.
Published: (2021-04-01)

Event-Based Trajectory Prediction Using Spiking Neural Networks
by: Guillaume Debat, et al.
Published: (2021-05-01)

Spiking Neural Network Learning, Benchmarking, Programming and Executing
Published: (2020)

Deep Liquid State Machines With Neural Plasticity for Video Activity Recognition
by: Nicholas Soures, et al.
Published: (2019-07-01)

SpiLinC: Spiking Liquid-Ensemble Computing for Unsupervised Speech and Image Recognition
by: Gopalakrishnan Srinivasan, et al.
Published: (2018-08-01)

Machine Learning for Traffic Control of Unmanned Mining Machines : Using the Q-learning and SARSA algorithms
by: Gustafsson, Robin, et al.
Published: (2019)

Single asset trading: a recurrent reinforcement learning approach
by: Nikolic, Marko
Published: (2020)

MARLA-SG: Multi-Agent Reinforcement Learning Algorithm for Efficient Demand Response in Smart Grid
by: Sally Aladdin, et al.
Published: (2020-01-01)

A Neuromorphic-Hardware Oriented Bio-Plausible Online-Learning Spiking Neural Network Model
by: G. C. Qiao, et al.
Published: (2019-01-01)

An Adaptive Strategy Selection Method With Reinforcement Learning for Robotic Soccer Games
by: Haobin Shi, et al.
Published: (2018-01-01)

Solution Of Delayed Reinforcement Learning Problems Having Continuous Action Spaces
by: Ravindran, B
Published: (2012)

A reinforcement learning model for personalized driving policies identification
by: Dimitris M. Vlachogiannis, et al.
Published: (2020-12-01)

An Efficient Hardware Implementation of Reinforcement Learning: The Q-Learning Algorithm
by: Sergio Spano, et al.
Published: (2019-01-01)

A Reinforcement Learning Approach to Dynamic Scheduling in a Product-Mix Flexibility Environment
by: Yeou-Ren Shiue, et al.
Published: (2020-01-01)

A Memristor-Based Liquid State Machine for Auditory Signal Recognition
by: Henderson, Stephen Alexander, Jr.
Published: (2021)

sPyNNaker: A Software Package for Running PyNN Simulations on SpiNNaker
by: Oliver Rhodes, et al.
Published: (2018-11-01)

A Reinforcement Learning-Based QAM/PSK Symbol Synchronizer
by: Marco Matta, et al.
Published: (2019-01-01)

Structured exploration for reinforcement learning
by: Jong, Nicholas K.
Published: (2012)

Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms
by: Kostas Bavarinos, et al.
Published: (2021-01-01)

Asymptotics of Reinforcement Learning with Neural Networks
by: Sirignano, J., et al.
Published: (2022)

Classification of Seismic Vulnerability Based on Machine Learning Techniques for RC Frames
by: Seyed Hooman Ghasemi, et al.
Published: (2020-04-01)

Reinforcement Learning with Auxiliary Memory
by: Suggs, Sterling
Published: (2021)

A study of model-based average reward reinforcement learning
by: Ok, DoKyeong
Published: (2012)

Studying a Reinforcement Learning Technique for the Spiking Neural Network
by: A. V. Kozov, et al.
Published: (2016-01-01)

Exploring Deep Recurrent Q-Learning for Navigation in a 3D Environment
by: Rasmus Kongsmar Brejl, et al.
Published: (2018-01-01)

Intelligent Algorithmic Trading Strategy Using Reinforcement Learning and Directional Change
by: Monira Essa Aloud, et al.
Published: (2021-01-01)

Deep Reinforcement Learning for Drone Delivery
by: Guillem Muñoz, et al.
Published: (2019-09-01)

Parallel Implementation of Reinforcement Learning Q-Learning Technique for FPGA
by: Lucileide M. D. Da Silva, et al.
Published: (2019-01-01)

Online Radio Pattern Optimization Based on Dual Reinforcement-Learning Approach for 5G URLLC Networks
by: Ali A. Esswie, et al.
Published: (2020-01-01)

Physics-based reinforcement learning for autonomous manipulation
by: Scholz, Jonathan
Published: (2016)

Cannot write session to /tmp/vufind_sessions/sess_cd6nqjf28gr7di4vf5ngp21nuq