[论文解读] Explanatory models in neuroscience: Part 1 -- taking mechanistic abstraction seriously

Rosa Cao, Daniel Yamins|arXiv (Cornell University)|Apr 3, 2021

Neural dynamics and brain function参考文献 58被引用 49

一句话总结

本文主张在强化的 3M++ 框架下，某些神经网络模型可以成为脑功能的机械解释，并引入可运行的抽象和相似性变换，将模型映射到脑机制。

ABSTRACT

Despite the recent success of neural network models in mimicking animal performance on visual perceptual tasks, critics worry that these models fail to illuminate brain function. We take it that a central approach to explanation in systems neuroscience is that of mechanistic modeling, where understanding the system is taken to require fleshing out the parts, organization, and activities of a system, and how those give rise to behaviors of interest. However, it remains somewhat controversial what it means for a model to describe a mechanism, and whether neural network models qualify as explanatory. We argue that certain kinds of neural network models are actually good examples of mechanistic models, when the right notion of mechanistic mapping is deployed. Building on existing work on model-to-mechanism mapping (3M), we describe criteria delineating such a notion, which we call 3M++. These criteria require us, first, to identify a level of description that is both abstract but detailed enough to be "runnable", and then, to construct model-to-brain mappings using the same principles as those employed for brain-to-brain mapping across individuals. Perhaps surprisingly, the abstractions required are those already in use in experimental neuroscience, and are of the kind deployed in the construction of more familiar computational models, just as the principles of inter-brain mappings are very much in the spirit of those already employed in the collection and analysis of data across animals. In a companion paper, we address the relationship between optimization and intelligibility, in the context of functional evolutionary explanations. Taken together, mechanistic interpretations of computational models and the dependencies between form and function illuminated by optimization processes can help us to understand why brain systems are built they way they are.

研究动机与目标

• 澄清在系统神经科学中什么算作机械解释。
• 提出一个扩展的模型-机制-映射标准（3M++），以容纳神经网络。
• 解释抽象、可运行模型和相似性变换如何支持模型到脑的映射。
• 提供来自神经科学的基础抽象以支撑 3M++。

提出的方法

• 回顾并综合机械解释文献（3M）与干预因果关系概念。
• 通过在 3M 中加入 Predictively Adequate Runnable Abstraction（PARA）和 Transform Similarity 来定义 3M++。
• 形式化抽象如何可运行并在目标现象上具因果充分性。
• 以腹侧视觉通路为案例研究，将分层卷积模型映射到大脑区域。
• 讨论抽象神经网络如何与生物学的尖峰网络和 LN 单位相关。

实验结果

研究问题

• RQ1 使用计算模型来建模脑功能时，什么算作解释性？
• RQ2 在尊重抽象层级的同时，如何将神经网络映射到脑机制？
• RQ3 哪些标准（3M++）最能确保模型在神经科学中是机械且具有解释性的？
• RQ4 何时抽象成为可运行且对新输入具有预测性？
• RQ5 相似性变换如何促进跨个体的脑到模型映射？

主要发现

• 在扩展的 3M++ 框架下，神经网络可以是具有解释性的模型。
• 通过可运行的抽象和跨个体的相似性映射，可以实现机械映射。
• 来自神经科学的基础抽象（例如 LN 单位、视网膜颊映射、分层处理）与计算模型结构如 HCNNs 对齐。
• 在某些情况下，深度神经网络可以提供抽象的机械解释，桥接模型表现和大脑机制。
• 基于实验神经科学抽象的框架支持评估旧模型和新模型的机械解释。