Reservoir Computing with Both Neuronal Intrinsic Plasticity and Multi-Clustered Structure
Reservoir Computing with Both Neuronal Intrinsic Plasticity and Multi-Clustered Structure
复制标题
兼具神经元固有可塑性和多簇结构的储层计算
DOI：
10.1007/s12559-017-9467-3
复制
发表时间：
2017-05
影响因子：
5.4
通讯作者：
Li Xiumin
中科院分区：
文献类型：
--
作者：
Xue Fangzheng;Li Qian;Zhou Hongjun;Li Xiumin
在回声状态网络中，水库状态和网络结构对于水库计算的性能至关重要。在神经科学中，已经证实单个神经元可以自适应地改变其内在兴奋性以适应各种突触输入。这种机制在文献中被称为内禀塑性（IP）机制。神经元对外部输入的反应的这种自适应调整被认为是最大化输入-输出互信息。与此同时，脑内具有小世界性质的多簇结构的存在也得到了许多神经生理学实验的有力支持。因此，建议考虑油藏网络的内在塑性和多簇结构，而不是具有非自适应油藏响应的随机网络。本文研究了具有神经元内在可塑性和多簇结构的水库模型。两种类型的IP规则的性能上的几个计算任务的影响进行了详细的研究，结合神经元IP与多集群水库结构。第一种是Triesch的IP规则，它驱动神经元的输出活动近似指数分布;另一种是Li的IP规则，它产生神经元放电的高斯分布。结果表明，多簇结构和IP规则都能提高油藏计算的精度。然而，在应用IP规则之前，对于多组油藏的计算性能的提高是微小的。两种IP规则都有助于提高计算性能，其中Li的IP规则比Triesch的IP规则更有优势。结果表明，多组储层结构与IP学习相结合，可以增加储层状态的动态多样性，尤其是IP学习。基于IP的水库状态的自适应调整改善了神经元活动的动态复杂性，这有助于训练输出权重。这种生物启发的储层模型可以为储层计算的优化提供见解。
In the echo state networks, both reservoir states and network structure are essential for the performance of reservoir computing. In neuroscience, it has been confirmed that a single neuron can adaptively change its intrinsic excitability to fit various synaptic inputs. This mechanism is called intrinsic plasticity (IP) mechanism in the literature. This adaptive adjustment of neuronal response to external inputs is believed to maximize input-output mutual information. Meanwhile, the existence of multi-clustered structure with small-world-like property in the brain has been strongly supported by many neurophysiological experiments. Thus, it is advisable to consider both the intrinsic plasticity and multi-clustered structure of a reservoir network, rather than a random network with a non-adaptive reservoir response. In this paper, reservoir models with neuronal intrinsic plasticity and multi-clustered structure are investigated. The effects of two types of IP rules on the performance of several computational tasks have been investigated in detail by combining neuronal IP with multi-clustered reservoir structures. The first type is the Triesch’s IP rule, which drives the output activities of neurons to approximate exponential distributions; another is the Li’s IP rule, which generates a Gaussian distribution of neuronal firing. Results show that both the multi-clustered structures and IP rules can improve the computational accuracy of reservoir computing. However, before the application of the IP rules, the enhancement of computational performance for multi-clustered reservoirs is minor. Both IP rules contribute to improvement of the computational performance, where the Li’s IP rule is more advantageous than the Triesch’s IP. The results indicate that the combination of multi-clustered reservoir structures and IP learning can increase the dynamic diversity of reservoir states, especially for the IP’s learning. The adaptive tuning of reservoir states based on IP improves the dynamic complexity of neuronal activity, which helps train output weights. This biologically inspired reservoir model may give insights for the optimization of reservoir computing.
登录
查看更多内容
DOI：
10.1007/978-3-319-11179-7_4
发表时间：
2014-09
期刊：
--
影响因子：
--
作者：
P. Koprinkova-Hristova
通讯作者：
P. Koprinkova-Hristova
DOI：
10.1109/ijcnn.2015.7280703
发表时间：
2015-07
期刊：
2015 International Joint Conference on Neural Networks (IJCNN)
影响因子：
--
作者：
P. Koprinkova-Hristova
通讯作者：
P. Koprinkova-Hristova
影响因子：
3.7
作者：
Froemke RC;Debanne D;Bi GQ
通讯作者：
Bi GQ
影响因子：
5.4
作者：
R. Sun;Nicholas R. Wilson;M. Lynch
通讯作者：
R. Sun;Nicholas R. Wilson;M. Lynch
DOI：
10.1109/tasl.2007.896669
发表时间：
2007-07-01
影响因子：
--
作者：
Skowronski, Mark D.;Harris, John G.
通讯作者：
Harris, John G.