Cognitive Computational Neuroscience Group, University Erlangen-Nuremberg, Erlangen, Germany.
Pattern Recognition Lab, University Erlangen-Nuremberg, Erlangen, Germany.
Sci Rep. 2022 Jul 4;12(1):11233. doi: 10.1038/s41598-022-14916-1.
How does the mind organize thoughts? The hippocampal-entorhinal complex is thought to support domain-general representation and processing of structural knowledge of arbitrary state, feature and concept spaces. In particular, it enables the formation of cognitive maps, and navigation on these maps, thereby broadly contributing to cognition. It has been proposed that the concept of multi-scale successor representations provides an explanation of the underlying computations performed by place and grid cells. Here, we present a neural network based approach to learn such representations, and its application to different scenarios: a spatial exploration task based on supervised learning, a spatial navigation task based on reinforcement learning, and a non-spatial task where linguistic constructions have to be inferred by observing sample sentences. In all scenarios, the neural network correctly learns and approximates the underlying structure by building successor representations. Furthermore, the resulting neural firing patterns are strikingly similar to experimentally observed place and grid cell firing patterns. We conclude that cognitive maps and neural network-based successor representations of structured knowledge provide a promising way to overcome some of the short comings of deep learning towards artificial general intelligence.
思维如何组织思想？海马体-内嗅皮层复合体被认为支持任意状态、特征和概念空间的结构知识的领域通用表示和处理。特别是，它能够形成认知地图，并在这些地图上进行导航，从而为认知做出广泛贡献。有人提出，多尺度后继表示的概念为位置和网格细胞执行的基础计算提供了一个解释。在这里，我们提出了一种基于神经网络的方法来学习这种表示，并将其应用于不同的场景：基于监督学习的空间探索任务、基于强化学习的空间导航任务以及通过观察示例句子推断语言结构的非空间任务。在所有场景中，神经网络通过构建后继表示正确地学习和近似底层结构。此外，所得的神经放电模式与实验观察到的位置和网格细胞放电模式非常相似。我们得出结论，认知地图和基于神经网络的结构化知识后继表示为克服深度学习在人工智能方面的一些缺点提供了一种很有前途的方法。
