[论文解读] The neuroconnectionist research programme

Adrien Doerig, Rowan P. Sommers+9 more|arXiv (Cornell University)|Sep 8, 2022

EEG and Brain-Computer Interfaces被引用 24

一句话总结

该论文主张将人工神经网络视为一个连贯的、规模庞大的神经连接主义研究计划，受到 Lakatos 的启发，用以生成可证伪的关于大脑计算的理论，并随时间检验神经科学假设。

ABSTRACT

Artificial Neural Networks (ANNs) inspired by biology are beginning to be widely used to model behavioral and neural data, an approach we call neuroconnectionism. ANNs have been lauded as the current best models of information processing in the brain, but also criticized for failing to account for basic cognitive functions. We propose that arguing about the successes and failures of a restricted set of current ANNs is the wrong approach to assess the promise of neuroconnectionism. Instead, we take inspiration from the philosophy of science, and in particular from Lakatos, who showed that the core of scientific research programmes is often not directly falsifiable, but should be assessed by its capacity to generate novel insights. Following this view, we present neuroconnectionism as a cohesive large-scale research programme centered around ANNs as a computational language for expressing falsifiable theories about brain computation. We describe the core of the programme, the underlying computational framework and its tools for testing specific neuroscientific hypotheses. Taking a longitudinal view, we review past and present neuroconnectionist projects and their responses to challenges, and argue that the research programme is highly progressive, generating new and otherwise unreachable insights into the workings of the brain.

研究动机与目标

• 推动从评估受限的 ANN 模型转向评估一个连贯、进步的研究计划。
• 界定神经连接主义的核心概念、框架与工具，以测试大脑计算假设。
• 论证纵向、迭代式进展能够产生超越单一模型成功的新见解。
• 将神经连接主义定位为对建模认知和神经数据的科学严谨方法。

提出的方法

• 提出一个连贯的计算框架，其中人工神经网络表达关于大脑计算的可证伪理论。
• 描述在该计划内测试特定神经科学假设的工具和方法。
• 采用纵向、受 Lakatos 启发的视角来评估进展，超越即时模型性能。

实验结果

研究问题

• RQ1 神经连接主义研究计划的核心由哪些组成？
• RQ2 人工神经网络如何作为表达和测试可证伪的大脑理论的计算语言？
• RQ3 拉卡托斯式的科学观是否能够证明神经连接主义项目随着时间产生的进展和新颖性？
• RQ4 在该计划中测试神经科学假设需要什么框架和工具？

主要发现

• 神经连接主义方法将 ANN 的使用重新定位为一个连贯、进步的研究计划的一部分，而非孤立的模型。
• 受 Lakatos 启发的视角帮助通过其产生新见解的能力来评估该计划，而非对单个模型的即时可证伪性。
• 本文概述了在神经连接主义中评估神经科学假设所需的核心计算框架与测试工具。
• 纵向回顾表明过去与现在的项目回应挑战并产生关于大脑计算的洞见。
• 该计划旨在产生仅用单一模型评估难以获得的洞见。