论文标题
迈向语言的神经架构：构图处理的神经体系结构访问的深度学习与物流
Towards a neural architecture of language: Deep learning versus logistics of access in neural architectures for compositional processing
论文作者
论文摘要
最近，许多文章认为，诸如GPT之类的深度学习模型也可以捕获人类思想和大脑中语言处理的关键方面。但是，我将认为这些模型不适合作为人类语言的神经模型。首先，因为它们在基本的边界条件下失败，例如所需的学习量。实际上，这意味着GPT和大脑语言处理的机制在根本上是不同的。其次，因为它们不具备构图和生产性人类语言处理所需的访问物流。神经体系结构可以基于网络结构（例如网络结构）具有访问的物流，其中处理不是由符号操纵组成，而是控制激活的流动。在这种观点中，需要两种补充方法来研究大脑与认知之间的关系。研究学习方法可以揭示深度学习中在大脑中发现的“学习认知”如何。但是，还应开发具有访问物流的神经体系结构，以说明自然或人工语言处理所需的“生产认知”。后来，可能会合并这些方法，以了解这些架构如何通过更简单的基础学习和开发来发展。
Recently, a number of articles have argued that deep learning models such as GPT could also capture key aspects of language processing in the human mind and brain. However, I will argue that these models are not suitable as neural models of human language. Firstly, because they fail on fundamental boundary conditions, such as the amount of learning they require. This would in fact imply that the mechanisms of GPT and brain language processing are fundamentally different. Secondly, because they do not possess the logistics of access needed for compositional and productive human language processing. Neural architectures could possess logistics of access based on small-world like network structures, in which processing does not consist of symbol manipulation but of controlling the flow of activation. In this view, two complementary approaches would be needed to investigate the relation between brain and cognition. Investigating learning methods could reveal how 'learned cognition' as found in deep learning could develop in the brain. However, neural architectures with logistics of access should also be developed to account for 'productive cognition' as required for natural or artificial human language processing. Later on, these approaches could perhaps be combined to see how such architectures could develop by learning and development from a simpler basis.
