Rieznik Andrés, Di Tella Rocco, Schvartzman Lara, Babino Andrés
Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Buenos Aires, Argentina.
INCYT, CONICET-INECO, Buenos Aires, Argentina.
Front Neurorobot. 2021 May 28;15:670895. doi: 10.3389/fnbot.2021.670895. eCollection 2021.
Connectionist and dynamic field models consist of a set of coupled first-order differential equations describing the evolution in time of different units. We compare three numerical methods for the integration of these equations: the Euler method, and two methods we have developed and present here: a modified version of the fourth-order Runge Kutta method, and one semi-analytical method. We apply them to solve a well-known nonlinear connectionist model of retrieval in single-digit multiplication, and show that, in many regimes, the semi-analytical and modified Runge Kutta methods outperform the Euler method, in some regimes by more than three orders of magnitude. Given the outstanding difference in execution time of the methods, and that the EM is widely used, we conclude that the researchers in the field can greatly benefit from our analysis and developed methods.
联结主义和动态场模型由一组描述不同单元随时间演化的耦合一阶微分方程组成。我们比较了三种用于这些方程积分的数值方法:欧拉方法,以及我们在此开发并展示的两种方法:四阶龙格 - 库塔方法的改进版本和一种半解析方法。我们将它们应用于求解一个著名的关于个位数乘法检索的非线性联结主义模型,并表明,在许多情况下,半解析方法和改进的龙格 - 库塔方法优于欧拉方法,在某些情况下优势超过三个数量级。鉴于这些方法在执行时间上的显著差异,且欧拉方法被广泛使用,我们得出结论,该领域的研究人员可以从我们的分析和开发的方法中大大受益。