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 2106.00790q-bio.NCcond-mat.dis-nncs.AI
收藏

对象流形神经处理的统计力学

Statistical Mechanics of Neural Processing of Object Manifolds

Harvard University(哈佛大学)

SueYeon Chung

摘要:

不变物体识别是大脑执行的最基本的认知任务之一。在神经状态空间中,不同的刺激变量对象被表示为不同的流形。在这个几何的角度来看,对象识别成为线性分离不同的对象流形的问题。在前馈视觉层次中,已经建议跨层重新格式化对象流形表示,以变得更加线性可分离。因此,一个完整的感知理论需要表征线性读出网络从可变神经反应中对物体流形进行分类的能力。孤立点感知机理论是由E.加德纳将其表述为统计力学问题,并使用复制理论进行分析。本文综合高维信号的统计和几何性质,推广了Gardner的分析,建立了流形的线性分类理论。[..]接下来,我们将我们的理论进一步推广到一般感知流形的线性分类,如点云。证明了流形的容量由有效半径R_M和有效维数D_M决定。最后,我们展示了扩展相关的应用程序,以真实的数据,将相关的流形,异质流形几何,稀疏标签和非线性分类。然后,我们演示了基于对象的流形如何在标准深度网络中转换。本论文为神经元处理对象的计算理论奠定了基础,为对象流形的线性可分性提供了定量的度量。我们希望这一理论将为生物和人工神经网络中感觉表征处理的计算原理提供新的见解。

英文摘要:

Invariant object recognition is one of the most fundamental cognitive tasks performed by the brain. In the neural state space, different objects with stimulus variabilities are represented as different manifolds. In this geometrical perspective, object recognition becomes the problem of linearly separating different object manifolds. In feedforward visual hierarchy, it has been suggested that the object manifold representations are reformatted across the layers, to become more linearly separable. Thus, a complete theory of perception requires characterizing the ability of linear readout networks to classify object manifolds from variable neural responses. A theory of the perceptron of isolated points was pioneered by E. Gardner who formulated it as a statistical mechanics problem and analyzed it using replica theory. In this thesis, we generalize Gardner's analysis and establish a theory of linear classification of manifolds synthesizing statistical and geometric properties of high dimensional signals. [..] Next, we generalize our theory further to linear classification of general perceptual manifolds, such as point clouds. We identify that the capacity of a manifold is determined that effective radius, R_M, and effective dimension, D_M. Finally, we show extensions relevant for applications to real data, incorporating correlated manifolds, heterogenous manifold geometries, sparse labels and nonlinear classifications. Then, we demonstrate how object-based manifolds transform in standard deep networks. This thesis lays the groundwork for a computational theory of neuronal processing of objects, providing quantitative measures for linear separability of object manifolds. We hope this theory will provide new insights into the computational principles underlying processing of sensory representations in biological and artificial neural networks.

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。

↑