Creating functionally favorable neural dynamics by maximizing information capacity
Creating functionally favorable neural dynamics by maximizing information capacity
复制标题
DOI：
10.1016/j.neucom.2020.03.008
复制
发表时间：
2020-08-04
期刊：
影响因子：
6
通讯作者：
Ching，ShiNung
中科院分区：
文献类型：
--
作者：
Ghazizadeh，Elham;Ching，ShiNung
优化和机器学习中普遍存在的问题涉及在动态环境中执行所需行为的系统设计。例如，稳定倒立摆的控制系统的经典示例。在本文中，我们考虑一个补充性且研究较少的问题：环境本身的设计。也就是说，我们能否创建一个动态系统，以通用但数学上严格的方式，很容易被未知代理“使用”。我们对神经元动力学的合成特别感兴趣，这些神经元动力学对于传入输入来说是最不稳定的。也就是说，我们能否创建能够很好地传播信息的神经动力学。为此，我们将控制理论和信息理论的思想结合起来，具体转向赋权的概念，或者动态系统在输入到状态意义上的信息能力。我们设计了一种策略来优化系统的动态，使用对系统状态空间的授权作为目标函数。这导致了一般有利于信息传播的动态。例如，优化的环境有望作为（传入输入分布的）编码器表现良好。我们概述了执行优化所需的关键技术创新，并通过示例讨论了根据此原理优化的系统的紧急动态特性。
A ubiquitous problem in optimization and machine learning pertains to the design of systems that enact a desired behavior in dynamical environments. For example, the classical example of a control system that stabilizes an inverted pendulum. In this paper, we consider a complementary and less well-studied problem: the design of the environment itself. That is, can we create a dynamical system that in a general but mathematically rigorous way, is readily ‘usable’ by an unknown agent. We are especially interested in the synthesis of neuronal dynamics that are maximally labile with respect to afferent inputs. That is, can we create neural dynamics that propagate information well. To do so, we blend ideas from control and information theories, by turning specifically to the notion of empowerment, or the information capacity of a dynamical system in an input-to-state sense. We devise a strategy to optimize the dynamics of a system using empowerment over its state space as an objective function. This results in dynamics that are generically conducive to information propagation. For example, the optimized environment would be expected to perform well as an encoder (of afferent input distributions). We outline the key technical innovations needed in order to perform the optimization and, by means of example, discuss emergent dynamical characteristics of systems optimized according to this principle.