Mikail Rubinov谈人工神经网络和生物神经网络区别


NeuroTimes | Oct. 24, 2015



Mikail Rubinov在Nature上对Rafael Yuste的文章(Nat. Rev. Neurosci. 16, 487–497 (2015))作出评论,认为他在谈及人工神经网络(artificial neural network)的研究历史时,并没有很好的区分人工神经网络模型(artificial neural network models)和生物神经网络模型(biological neural network models)。

Mikail Rubinov总结,神经科学专业研究的生物神经网络模型,是对真实神经系统的概括性不严密的经验模型,通过分布式计算产生复杂脑功能:broadly and imprecisely defined as empirically valid models of (embodied) neuronal or brain systems, which enable the emergence of complex brain function through distributed computation。

而人工智能和计算机专业研究的人工神经网络模型,是相对明确的网络结构,最初试图为复杂脑功能建模,现在却被视为一种受生物启发的数据分析算法,用于许多不同的科学领域,而不仅仅是生物/神经领域:a relatively well-defined class of networks originally designed to model complex brain function but now mainly viewed as a class of biologically inspired data-analysis algorithms useful in diverse scientific fields.

Rafael Yuste的回复:http://www.nature.com/nrn/journal/vaop/ncurrent/full/nrn4043.html

Rafael Yuste回复全文:http://docdro.id/hzK3L0W




分享到


© 2014-2015 NeuroTimes