Learning by Stimulation Avoidance as a Primary Principle of Spiking Neural Networks Dynamics
Learning by Stimulation Avoidance as a Primary Principle of Spiking Neural Networks Dynamics
复制标题
通过避免刺激进行学习作为尖峰神经网络动力学的主要原理
DOI：
10.7551/978-0-262-33027-5-ch037
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
T. Ikegami
中科院分区：
文献类型：
--
作者：
Lana Sinapayen;A. Masumori;N. Virgo;T. Ikegami
奖励概念的实际实施对基于人工生命的系统可以学习什么以及如何学习有着深刻的影响。系统如何区分有用的行为和有害的行为？在本文中，我们实现奖励/惩罚的刺激去除/应用程序的经常性尖峰神经网络与尖峰定时依赖可塑性。这种实现在神经元层面体现了奖励的概念，使学习机制在网络中无处不在。我们表明，这种低级学习可扩展到网络级别：网络纯粹通过与环境交互来学习任意时空放电模式，从一个几乎没有知识的随机初始状态开始。这种方法产生快速，噪声鲁棒的结果。
Practical implementation of the concept of reward has deep implications on what artificial-life based systems can learn and how they learn it. How can a system distinguish between useful behavior and harmful behavior? In this paper we implement reward/punishment as the removal/application of a stimulation to a recurrent spiking neural network with spiketiming dependent plasticity. This implementation embodies the concept of reward at the level of the neuron, making learning mechanisms ubiquitous to the network. We show that this low-level learning scales up to the network level: the network learns arbitrary spatio-temporal firing patterns purely by interacting with the environment, from a random initial state where virtually no knowledge is available. This approach yields fast, noise-robust results.