Shaping dynamical neural computations using spatiotemporal constraints
Shaping dynamical neural computations using spatiotemporal constraints
复制标题
DOI：
10.1016/j.bbrc.2024.150302
复制
发表时间：
2024-07-04
影响因子：
3.1
通讯作者：
Parkes，Linden
中科院分区：
文献类型：
--
作者：
Kim，Jason Z.;Larsen，Bart;Parkes，Linden
动力学在计算中起着至关重要的作用。随着时间的推移，状态的原则性进化使生物和人工网络能够表示和整合信息以做出决策。在过去的几十年里，在弥合我们如何理解生物计算与人工计算之间的差距方面，包括如何将从一个方面获得的见解转化为另一个方面，已经取得了重大的多学科进展。研究表明，神经生物学是大脑网络结构的一个关键决定因素，它产生了时空限制的活动模式，这些模式是计算的基础。在这里，我们讨论了神经系统如何使用动力学进行计算，并声称可以利用塑造大脑网络的生物约束来改善人工神经网络的实现。为了使这一讨论形式化，我们考虑了一种被广泛用于神经计算建模的大脑的自然人工模拟：递归神经网络（RNN）。在大脑和RNN中，我们强调了动力学发生的共同计算基底-神经元之间的连接性，并探索了生物物理约束（如资源效率，空间嵌入和神经发育）提供的独特计算优势。
Dynamics play a critical role in computation. The principled evolution of states over time enables both biological and artificial networks to represent and integrate information to make decisions. In the past few decades, significant multidisciplinary progress has been made in bridging the gap between how we understand biologicalversusartificial computation, including how insights gained from one can translate to the other. Research has revealed that neurobiology is a key determinant of brain network architecture, which gives rise to spatiotemporally constrained patterns of activity that underlie computation. Here, we discuss how neural systems use dynamics for computation, and claim that the biological constraints that shape brain networks may be leveraged to improve the implementation of artificial neural networks. To formalize this discussion, we consider a natural artificial analog of the brain that has been used extensively to model neural computation: the recurrent neural network (RNN). In both the brain and the RNN, we emphasize the common computational substrate atop which dynamics occur—the connectivity between neurons—and we explore the unique computational advantages offered by biophysical constraints such as resource efficiency, spatial embedding, and neurodevelopment.