D'Haene Michiel, Hermans Michiel, Schrauwen Benjamin
ELIS Department, Ghent University, 9000 Ghent, Belgium
Neural Comput. 2014 Jun;26(6):1055-79. doi: 10.1162/NECO_a_00587. Epub 2014 Mar 31.
In the field of neural network simulation techniques, the common conception is that spiking neural network simulators can be divided in two categories: time-step-based and event-driven methods. In this letter, we look at state-of-the art simulation techniques in both categories and show that a clear distinction between both methods is increasingly difficult to define. In an attempt to improve the weak points of each simulation method, ideas of the alternative method are, sometimes unknowingly, incorporated in the simulation engine. Clearly the ideal simulation method is a mix of both methods. We formulate the key properties of such an efficient and generally applicable hybrid approach.
在神经网络模拟技术领域，普遍的观点是脉冲神经网络模拟器可分为两类：基于时间步长的方法和事件驱动的方法。在这封信中，我们研究了这两类中的先进模拟技术，并表明这两种方法之间越来越难以明确区分。为了改进每种模拟方法的弱点，有时会在不知不觉中将另一种方法的理念融入模拟引擎中。显然，理想的模拟方法是将这两种方法结合起来。我们阐述了这种高效且普遍适用的混合方法的关键特性。
