Competitive Maximization of Neuronal Activity in Convolutional Recurrent Spiking Neural Networks

机译：卷积复发尖峰神经网络中神经元活动的竞争最大化

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Spiking neural networks (SNNs) are the promising algorithm for specific neurochip hardware real-time solutions. SNNs are believed to be highly energy and computationally efficient. We focus on developing local learning rules that are capable to provide both supervised and unsupervised learning. We suppose that each neuron in a biological neural network tends to maximize its activity in competition with other neurons. This principle was put at the basis of SNN learning algorithm called FEELING. Here we introduce efficient Convolutional Recurrent Spiking Neural Network architecture that uses FEELING rules and provides better results than fully connected SNN on MNIST benchmark having 55 times less learnable weight parameters.

机译：尖峰神经网络（SNNS）是特定神经芯板硬件实时解决方案的有希望的算法。 SNNS被认为是高能量和计算效率。我们专注于开发能够提供监督和无人监督的学习的本地学习规则。我们认为生物网络中的每个神经元在与其他神经元竞争中倾向于最大化其活性。这一原则是以称为感觉的SNN学习算法的基础。在这里，我们介绍了使用感受规则的高效卷积复制尖峰神经网络架构，并提供比Mnist基准上的完全连接的SNN提供更好的结果，其具有55倍可被学习的重量参数。

著录项

来源
《International conference on neuroinformatics》|2020年|xvii 428 p.|共8页
会议地点
作者
Dmitry Nekhaev; Vyacheslav Demin;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类计算技术、计算机技术;
关键词
Spiking neural networks; Local learning rules;

机译：尖刺神经网络;本地学习规则;

相似文献

外文文献
中文文献
专利

1. Healthy human CSF promotes glial differentiation of hESC-derived neural cells while retaining spontaneous activity in existing neuronal networks Healthy human CSF promotes glial differentiation of hESC-derived neural cells while retaining spontaneous activity in existing neuronal networks Healthy human CSF promotes glial differentiation of hESC-derived neural cells while retaining spontaneous activity in existing neuronal networks [J] . Riikka ??nismaa, Heli Skottman, Heikki Kiiski, Biology Open . 2013,第6期

机译：健康的人类CSF促进hESC衍生的神经细胞的神经胶质分化，同时保留现有神经元网络的自发活动健康的人类CSF促进hESC衍生的神经细胞的神经胶质分化，同时保留现有神经元网络的自发活性健康的人类CSF促进hESC衍生的神经胶质分化。神经细胞，同时保留现有神经网络中的自发活动
2. Wind speed forecasting system based on gated recurrent units and convolutional spiking neural networks [J] . Wei Danxiang, Wang Jianzhou, Niu Xinsong, Applied Energy . 2021,第Juna15期

机译：基于门控复发单位的风速预测系统和卷积尖峰神经网络
3. Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks III: Partially connected neurons driven by spontaneous activity [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：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III：由自发活动驱动的部分连接的神经元
4. Competitive Maximization of Neuronal Activity in Convolutional Recurrent Spiking Neural Networks [C] . Dmitry Nekhaev, Vyacheslav Demin International conference on neuroinformatics . 2020

机译：卷积复发尖峰神经网络中神经元活动的竞争最大化
5. Deep Neural Language Model for Text Classification Based on Convolutional and Recurrent Neural Networks [D] . Hassan, Abdalraouf. 2018

机译：基于卷积神经网络和递归神经网络的深度神经语言文本分类模型
6. Recurrent Spiking Neural Network Learning Based on a Competitive Maximization of Neuronal Activity [O] . Vyacheslav Demin, Dmitry Nekhaev 2018

机译：基于神经元活动竞争最大化的递归尖峰神经网络学习
7. Human activity recognition and classification using of convolutional neural networks and recurrent neural networks [O] . Mohammed ALBABA, Alhakam QASSAB, Arif YILMAZ 2020

机译：人类活动认可与卷积神经网络和经常性神经网络的分类

Competitive Maximization of Neuronal Activity in Convolutional Recurrent Spiking Neural Networks

摘要

著录项

相似文献

相关主题

期刊订阅