Neural population geometry: An approach for understanding biological and artificial neural networks.

Neural population geometry: An approach for understanding biological and artificial neural networks.
复制标题

神经种群几何学:一种理解生物和人工神经网络的方法。

DOI:
10.1016/j.conb.2021.10.010
复制
发表时间:
2021-10
影响因子:
5.7
通讯作者:
--
中科院分区:
医学2区
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

实验神经科学的进步改变了我们探索神经回路结构和功能的能力。与此同时,机器学习的进步释放了人工神经网络(ANN)非凡的计算能力。虽然这两个领域拥有不同的工具和应用,但它们提出了一个相似的挑战:即理解信息是如何通过高维表示嵌入和处理以解决复杂任务的。解决这一挑战的一种方法是利用数学和计算工具来分析这些高维表示的几何,即神经种群几何。我们回顾了提供对生物和人工神经网络功能的洞察的几何方法的例子:感知中的表征解缠,认知系统中分类能力的几何理论,认知系统中的解缠和抽象,认知地图中的拓扑表示,运动系统中的动态解缠,以及认知的动力学方法。综上所述,这些发现说明了机器学习、神经科学和几何学交叉领域的一个令人兴奋的趋势,其中神经种群几何为任务执行提供了一个有用的种群级别的机械描述符。重要的是,几何描述适用于感觉模式、大脑区域、网络架构和时间尺度。因此,神经种群几何有可能统一我们对生物和人工神经网络中结构和功能的理解,弥合单个神经元、种群活动和行为之间的差距。
Advances in experimental neuroscience have transformed our ability to explore the structure and function of neural circuits. At the same time, advances in machine learning have unleashed the remarkable computational power of artificial neural networks (ANNs). While these two fields have different tools and applications, they present a similar challenge: namely, understanding how information is embedded and processed through high-dimensional representations to solve complex tasks. One approach to addressing this challenge is to utilize mathematical and computational tools to analyze the geometry of these high-dimensional representations, i.e., neural population geometry. We review examples of geometrical approaches providing insight into the function of biological and artificial neural networks: representation untangling in perception, a geometric theory of classification capacity, disentanglement, and abstraction in cognitive systems, topological representations underlying cognitive maps, dynamic untangling in motor systems, and a dynamical approach to cognition. Together, these findings illustrate an exciting trend at the intersection of machine learning, neuroscience, and geometry, in which neural population geometry provides a useful population-level mechanistic descriptor underlying task implementation. Importantly, geometric descriptions are applicable across sensory modalities, brain regions, network architectures, and timescales. Thus, neural population geometry has the potential to unify our understanding of structure and function in biological and artificial neural networks, bridging the gap between single neurons, population activities, and behavior.
DOI: 10.7554/elife.03476
发表时间: 2014-08-20
期刊: eLife
影响因子: 7.7
作者:
Dabaghian Y;Brandt VL;Frank LM
通讯作者: Frank LM
DOI: 10.1109/pgec.1965.264137
发表时间: 1965-01-01
期刊: IEEE TRANSACTIONS ON ELECTRONIC COMPUTERS
影响因子: --
作者:
COVER, TM
通讯作者: COVER, TM
DOI: 10.1038/s41593-019-0377-4
发表时间: 2019-06-01
影响因子: 25
作者:
Henaff, Olivier J.;Goris, Robbe L. T.;Simoncelli, Eero P.
通讯作者: Simoncelli, Eero P.
DOI: 10.1016/j.cell.2020.09.031
发表时间: 2020-11-12
期刊: Cell
影响因子: 64.5
作者:
Bernardi S;Benna MK;Rigotti M;Munuera J;Fusi S;Salzman CD
通讯作者: Salzman CD
DOI: 10.1371/journal.pcbi.1003915
发表时间: 2014-11
影响因子: 4.3
作者:
Khaligh-Razavi SM;Kriegeskorte N
通讯作者: Kriegeskorte N