arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1602.04742cs.NEq-bio.NC
收藏

基于信息论代价的脉冲神经网络训练

Training of spiking neural networks based on information theoretic costs

Oleg Y. Sinyavskiy

摘要:

脉冲神经网络是一种神经元之间通过脉冲进行通信的人工神经网络。尖峰是由其到达时间表征的相同布尔事件。尖峰神经元具有内部动力学,并且响应于输入的历史,而不是仅响应于当前输入。由于这些特性,脉冲神经网络具有丰富的内在能力来处理时空数据。然而,由于尖峰是不连续的“是或否”事件,因此将传统的训练过程(例如梯度下降)应用于尖峰神经元并非微不足道。在这篇论文中,我们提出使用随机尖峰神经元模型,其中尖峰输出的概率是参数的连续函数。我们制定了几个学习任务的最小化某些信息理论的成本函数,使用尖峰输出概率分布。我们开发了一个广义的随机尖峰神经元和一个新的尖峰神经元模型,允许灵活地处理丰富的时空数据的描述。我们为以下任务制定和推导学习规则:- 检测时空模式作为负对数似然的最小化的监督学习任务,神经元输出的稳定性(熵)-一种无监督学习任务,以熵的最小化来增加神经元输出的稳定性-控制代理的强化学习任务,作为神经元输出的滤波后的样本的调制优化。我们测试了衍生的学习规则在几个实验中,如时空模式检测,时空数据存储和召回与自联想记忆,结合监督和无监督学习,以加快学习过程,简单的虚拟代理在不断变化的环境中的自适应控制。

英文摘要:

Spiking neural network is a type of artificial neural network in which neurons communicate between each other with spikes. Spikes are identical Boolean events characterized by the time of their arrival. A spiking neuron has internal dynamics and responds to the history of inputs as opposed to the current inputs only. Because of such properties a spiking neural network has rich intrinsic capabilities to process spatiotemporal data. However, because the spikes are discontinuous 'yes or no' events, it is not trivial to apply traditional training procedures such as gradient descend to the spiking neurons. In this thesis we propose to use stochastic spiking neuron models in which probability of a spiking output is a continuous function of parameters. We formulate several learning tasks as minimization of certain information-theoretic cost functions that use spiking output probability distributions. We develop a generalized description of the stochastic spiking neuron and a new spiking neuron model that allows to flexibly process rich spatiotemporal data. We formulate and derive learning rules for the following tasks: - a supervised learning task of detecting a spatiotemporal pattern as a minimization of the negative log-likelihood (the surprisal) of the neuron's output - an unsupervised learning task of increasing the stability of neurons output as a minimization of the entropy - a reinforcement learning task of controlling an agent as a modulated optimization of filtered surprisal of the neuron's output. We test the derived learning rules in several experiments such as spatiotemporal pattern detection, spatiotemporal data storing and recall with autoassociative memory, combination of supervised and unsupervised learning to speed up the learning process, adaptive control of simple virtual agents in changing environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑