Suppr超能文献

连接主义与动态场方程的最优整合程序

Optimum Integration Procedure for Connectionist and Dynamic Field Equations.

作者信息

Rieznik Andrés, Di Tella Rocco, Schvartzman Lara, Babino Andrés

机构信息

Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Buenos Aires, Argentina.

INCYT, CONICET-INECO, Buenos Aires, Argentina.

出版信息

Front Neurorobot. 2021 May 28;15:670895. doi: 10.3389/fnbot.2021.670895. eCollection 2021.

Abstract

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.

摘要

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。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/dcf0/8193506/db4b88c433ef/fnbot-15-670895-g0001.jpg

相似文献

1
Optimum Integration Procedure for Connectionist and Dynamic Field Equations.
Front Neurorobot. 2021 May 28;15:670895. doi: 10.3389/fnbot.2021.670895. eCollection 2021.
2
Stochastic Bayesian Runge-Kutta method for dengue dynamic mapping.
MethodsX. 2022 Dec 20;10:101979. doi: 10.1016/j.mex.2022.101979. eCollection 2023.
3
Free vibration of summation resonance of suspended-cable-stayed beam.
Math Biosci Eng. 2019 Aug 8;16(6):7230-7249. doi: 10.3934/mbe.2019363.
4
Simulation Study on Effects of Order and Step Size of Runge-Kutta Methods that Solve Contagious Disease and Tumor Models.
J Comput Sci Syst Biol. 2016 Sep;9(5):163-172. doi: 10.4172/jcsb.1000234. Epub 2016 Sep 30.
5
Propagators for the Time-Dependent Kohn-Sham Equations: Multistep, Runge-Kutta, Exponential Runge-Kutta, and Commutator Free Magnus Methods.
J Chem Theory Comput. 2018 Jun 12;14(6):3040-3052. doi: 10.1021/acs.jctc.8b00197. Epub 2018 May 9.
7
Optimal bang-bang control for variable-order dengue virus; numerical studies.
J Adv Res. 2021 Apr 2;32:37-44. doi: 10.1016/j.jare.2021.03.010. eCollection 2021 Sep.
8
Modeling and Solution of Reaction-Diffusion Equations by Using the Quadrature and Singular Convolution Methods.
Arab J Sci Eng. 2023;48(3):4045-4065. doi: 10.1007/s13369-022-07367-3. Epub 2022 Oct 21.
9
Upstream flood pattern recognition based on downstream events.
Environ Monit Assess. 2018 Apr 24;190(5):306. doi: 10.1007/s10661-018-6686-3.
10
Semi-computational simulation of magneto-hemodynamic flow in a semi-porous channel using optimal homotopy and differential transform methods.
Comput Biol Med. 2013 Sep;43(9):1142-53. doi: 10.1016/j.compbiomed.2013.05.019. Epub 2013 Jun 1.

本文引用的文献

1
Benchmarking Wearable Robots: Challenges and Recommendations From Functional, User Experience, and Methodological Perspectives.
Front Robot AI. 2020 Nov 13;7:561774. doi: 10.3389/frobt.2020.561774. eCollection 2020.
2
Personalizing Human-Agent Interaction Through Cognitive Models.
Front Psychol. 2020 Sep 24;11:561510. doi: 10.3389/fpsyg.2020.561510. eCollection 2020.
3
Autonomous Sequence Generation for a Neural Dynamic Robot: Scene Perception, Serial Order, and Object-Oriented Movement.
Front Neurorobot. 2019 Nov 15;13:95. doi: 10.3389/fnbot.2019.00095. eCollection 2019.
4
How Cognitive Models of Human Body Experience Might Push Robotics.
Front Neurorobot. 2019 Apr 11;13:14. doi: 10.3389/fnbot.2019.00014. eCollection 2019.
5
Dazzled by the Mystery of Mentalism: The Cognitive Neuroscience of Mental Athletes.
Front Hum Neurosci. 2017 May 31;11:287. doi: 10.3389/fnhum.2017.00287. eCollection 2017.
6
Arithmetic on Your Phone: A Large Scale Investigation of Simple Additions and Multiplications.
PLoS One. 2016 Dec 29;11(12):e0168431. doi: 10.1371/journal.pone.0168431. eCollection 2016.
7
Developing Dynamic Field Theory Architectures for Embodied Cognitive Systems with .
Front Neurorobot. 2016 Nov 2;10:14. doi: 10.3389/fnbot.2016.00014. eCollection 2016.
8
Are Individual Differences in Arithmetic Fact Retrieval in Children Related to Inhibition?
Front Psychol. 2016 Jun 14;7:825. doi: 10.3389/fpsyg.2016.00825. eCollection 2016.
9
Retrieval-induced forgetting of multiplication facts and identity rule.
Mem Cognit. 2015 May;43(4):672-80. doi: 10.3758/s13421-014-0483-1.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验