Hybrid neural networks--combining abstract and realistic neural units.
Hybrid neural networks--combining abstract and realistic neural units.
复制标题
混合神经网络——结合了抽象和现实的神经单元。
DOI：
10.1109/iembs.2004.1404116
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Hines,Michael
中科院分区：
文献类型：
--
作者：
Lytton,WilliamW;Hines,Michael
There is a trade-off in neural network simulation between simulations that embody the details of neuronal biology and those that omit these details in favor of abstractions. The former approach appeals to physiologists and pharmacologists who can directly relate their experimental manipulations to parameter changes in the model. The latter approach appeals to physicists and mathematicians who seek analytic understanding of the behavior of large numbers of coupled simple units. This simplified approach is also valuable for practical reasons a highly simplified unit will run several orders of magnitude faster than a complex, biologically realistic unit. In order to have our cake and eat it, we have developed hybrid networks in the Neuron simulator package. These make use of Neuron's local variable timestep method to permit simplified integrate-and-fire units to move ahead quickly while realistic neurons in the same network are integrated slowly.
