arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1610.02084cs.NEcs.DCq-bio.NC
收藏

生物神经网络中的计算权衡:自稳定赢家通吃网络

Computational Tradeoffs in Biological Neural Networks: Self-Stabilizing Winner-Take-All Networks

Nancy Lynch, Cameron Musco, Merav Parter

摘要:

我们从算法的角度对生物神经网络进行了研究。我们为随机脉冲神经网络中的分布式计算开发了一个简化但在生物学上合理的模型,并研究了该模型中计算时间和网络复杂性之间的权衡。我们的目标是抽象真实的神经网络,虽然不能捕捉所有有趣的特征,但可以保留高级行为,并允许我们做出生物相关的结论。在本文中,我们专注于重要的“赢家通吃”(WTA)的问题,这是类似于一个神经领袖选举单位:一个网络组成的$n$输入神经元和$n$相应的输出神经元必须收敛到一个状态,其中一个单一的输出对应于一个发射输入(“赢家”)火灾,而所有其他输出保持沉默。WTA的神经回路依赖于抑制性神经元,抑制性神经元抑制竞争输出的活动,并将网络推向一个具有单一触发赢家的收敛状态。我们试图了解所使用的抑制剂的数量如何影响网络收敛时间。我们表明,它是可能的,以显着优于天真的WTA结构,通过更精细的使用抑制,解决问题,在$O(θ)$轮的预期与$O(\log^{1/θ} n)$抑制剂的任何$θ$。另一种结构在$O(\log^{1/θ} n)$轮中用$O(θ)$抑制剂给出收敛性。我们称赞这些上限与我们的主要技术贡献,一个几乎匹配的下限网络使用$\ge \log\log n$抑制剂。我们的下限使用熟悉的不可扩展性和局部性参数从分布式计算理论。它让我们得出了一些有趣的结论,关于任何以良好概率解决WTA的网络的结构,以及在这样的网络中使用随机性和抑制性。

英文摘要:

We initiate a line of investigation into biological neural networks from an algorithmic perspective. We develop a simplified but biologically plausible model for distributed computation in stochastic spiking neural networks and study tradeoffs between computation time and network complexity in this model. Our aim is to abstract real neural networks in a way that, while not capturing all interesting features, preserves high-level behavior and allows us to make biologically relevant conclusions. In this paper, we focus on the important `winner-take-all' (WTA) problem, which is analogous to a neural leader election unit: a network consisting of $n$ input neurons and $n$ corresponding output neurons must converge to a state in which a single output corresponding to a firing input (the `winner') fires, while all other outputs remain silent. Neural circuits for WTA rely on inhibitory neurons, which suppress the activity of competing outputs and drive the network towards a converged state with a single firing winner. We attempt to understand how the number of inhibitors used affects network convergence time. We show that it is possible to significantly outperform naive WTA constructions through a more refined use of inhibition, solving the problem in $O(θ)$ rounds in expectation with just $O(\log^{1/θ} n)$ inhibitors for any $θ$. An alternative construction gives convergence in $O(\log^{1/θ} n)$ rounds with $O(θ)$ inhibitors. We compliment these upper bounds with our main technical contribution, a nearly matching lower bound for networks using $\ge \log\log n$ inhibitors. Our lower bound uses familiar indistinguishability and locality arguments from distributed computing theory. It lets us derive a number of interesting conclusions about the structure of any network solving WTA with good probability, and the use of randomness and inhibition within such a network.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑