Gradland: On Phenomenal Experience, Differentiated Across Many Dimensions

Gradland：关于现象体验，跨多维度的微分研究

Abstract: This paper investigates the hypothesis that the first-order structure of physical interactions, i.e. gradients or Jacobians, characterizes the structure of phenomenal experience. It does so in an idealized world inhabited by neural networks, Gradland, where the physics are known and the functions are (mostly) differentiable.

摘要： 本文探讨了一个假设，即物理相互作用的一阶结构（即梯度或雅可比矩阵）刻画了现象体验的结构。研究在一个由神经网络构成的理想化世界“Gradland”中进行，在该世界中，物理定律已知，且函数（大多）是可微的。

The paper introduces two measures of Jacobian structure: effective rank and cohesion, based on Kirchhoff complexity. Applying the measures to a series of worked examples shows the hypothesis accounts for: (1) the duration of experience, that it can prolong over hundreds of milliseconds; (2) the difference between what is experienced vividly and obscurely; (3) the experience of texture; (4) the blooming buzzing confusion presumably experienced by newborns; (5) the difference between ideas that are held distinctly in mind and ideas that are confused; (6) what learning is like; and finally (7) the paper explains the function of rich, dense experience.

本文引入了两种基于基尔霍夫复杂度（Kirchhoff complexity）的雅可比结构度量指标：有效秩（effective rank）和内聚性（cohesion）。将这些度量应用于一系列实例分析后表明，该假设可以解释：(1) 体验的持续时间，即体验可以延长至数百毫秒；(2) 清晰体验与模糊体验之间的差异；(3) 质感体验；(4) 新生儿可能经历的“繁花似锦的嗡嗡混乱”（blooming buzzing confusion）；(5) 头脑中清晰持有的概念与混乱概念之间的区别；(6) 学习的过程；以及最后 (7) 解释了丰富且密集的体验所具备的功能。