Spiking Reservoir Networks: Brain-Inspired Recurrent Algorithms That Use Random, Fixed Synaptic Strengths

Soures Nicholas; Kudithipudi Dhireesha

首页> 外文期刊>IEEE Signal Processing Magazine >Spiking Reservoir Networks: Brain-Inspired Recurrent Algorithms That Use Random, Fixed Synaptic Strengths

【24h】

Spiking Reservoir Networks: Brain-Inspired Recurrent Algorithms That Use Random, Fixed Synaptic Strengths

机译：尖刺水库网络：使用随机，固定突触强度的脑启发性递归算法

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

A class of brain-inspired recurrent algorithms known as < italic > reservoir computing (RC) networks reduces the computational complexity and cost of training machine-learning models by using random, fixed synaptic strengths. This article offers insights about a spiking reservoir network, the liquid state machine (LSM), the inner workings of the algorithm, the design metrics, and neuromorphic designs. The discussion extends to variations of the LSM that incorporate local plasticity mechanisms and hierarchy to improve performance and memory capacity.

机译：一类由脑启发式循环算法称为“斜体”（RC）网络，它通过使用随机的，固定的突触强度来降低训练机器学习模型的计算复杂度和成本。本文提供了有关尖峰油藏网络，液体状态机（LSM），算法的内部工作原理，设计指标和神经形态设计的见解。讨论扩展到LSM的各种变体，它们结合了局部可塑性机制和层次结构，以提高性能和存储容量。

著录项

来源
《IEEE Signal Processing Magazine》 |2019年第6期|78-87|共10页
作者
Soures Nicholas; Kudithipudi Dhireesha;
展开▼
作者单位

Rochester Inst Technol Comp Engn New York NY 14623 USA|IEEE Piscataway NJ 08854 USA;

IEEE Piscataway NJ 08854 USA|Rochester Inst Technol Neuromorph Artificial Intelligence Lab New York NY USA;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Neurons; Signal processing algorithms; Machine learning; Artificial neural networks; Neuromorphics; Bio-inspired computing; Brain modeling; Recurrent neural networks; Computational modeling;

机译：神经元;信号处理算法;机器学习;人工神经网络;神经形态学受生物启发的计算;大脑建模;递归神经网络;计算建模;

相似文献

外文文献
中文文献
专利

1. Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks IV - Structuring synaptic pathways among recurrent connections [J] . Gilson M, Burkitt AN, Grayden DB, Biological Cybernetics: Communication and Control in Organisms and Automata: = Nachrichtenubertragung, Nachrichtenverarbeitung, Steuerung und Regelung in Organismen und in Automaten . 2009,第5a6期

机译：递归神经元网络中由于穗定时依赖的可塑性引起的网络结构的出现IV-在递归连接中构建突触途径
2. Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks IV Structuring synaptic pathways among recurrent connections [J] . Matthieu Gilson, Anthony N. Burkitt, David B. Grayden, Biological Cybernetics . 2009,第5a6期

机译：复发性神经元网络中由于穗定时依赖的可塑性引起的网络结构的出现IV构建复发性连接之间的突触途径
3. Skip-Connected Self-Recurrent Spiking Neural Networks With Joint Intrinsic Parameter and Synaptic Weight Training [J] . Wenrui Zhang, Peng Li Neural computation . 2021,第7期

机译：用联合内在参数和突触重量训练跳过连接的自发性尖峰神经网络
4. Distance- and Direction-Dependent Synaptic Weight Distributions for Directional Spike Propagation in a Recurrent Network: Self-actuated Shutdown of Synaptic Plasticity [C] . Toshikazu Samura, Yutaka Sakai, Hatsuo Hayashi, International conference on neural information processing . 2013

机译：递归网络中定向穗传播的距离和方向依赖性突触权重分布：突触可塑性的自致动关闭。
5. Indirect Training Algorithms for Spiking Neural Networks based on Spiking Timing Dependent Plasticity and Their Applications. [D] . Zhang, Xu. 2017

机译：基于尖峰时序相关可塑性的尖峰神经网络间接训练算法及其应用。
6. Pre-Synaptic Pool Modification (PSPM): A supervised learning procedure for recurrent spiking neural networks [O] . Bryce Allen Bagley, Blake Bordelon, Benjamin Moseley, 2020

机译：突触前池修饰（PSPM）：一种针对周期性尖峰神经网络的监督学习程序
7. Skip-Connected Self-Recurrent Spiking Neural Networks With Joint Intrinsic Parameter and Synaptic Weight Training [O] . Wenrui Zhang, Peng Li 2021

机译：用联合内在参数和突触重量训练跳过连接的自发性尖峰神经网络

Spiking Reservoir Networks: Brain-Inspired Recurrent Algorithms That Use Random, Fixed Synaptic Strengths

摘要

著录项

相似文献

相关主题

期刊订阅