论文标题
网格单元及其在AI中的潜在应用
Grid cells and their potential application in AI
论文作者
论文摘要
自从2005年获得诺贝尔奖获得奖项以来，神经科学家对网格细胞进行了广泛的研究。随着动物的移动，它们的多尺度周期性射击率使环境铺平了环境，这对于路径整合至关重要。多个实验表明，网格单元还为其他表示，例如嗅觉，注意机制，想象的运动和概念组织发射，可能充当神经回收的一种形式，并显示了Tolman在1948年设想的认知图的可能性机制。在本文中，我们概述了网格细胞研究，因为它们的发现，神经科学和认知科学的作用以及人工智能研究的未来方向。
Since their Nobel Prize winning discovery in 2005, grid cells have been studied extensively by neuroscientists. Their multi-scale periodic firing rates tiling the environment as the animal moves around has been shown as critical for path integration. Multiple experiments have shown that grid cells also fire for other representations such as olfactory, attention mechanisms, imagined movement, and concept organization potentially acting as a form of neural recycling and showing the possible brain mechanism for cognitive maps that Tolman envisioned in 1948. Grid cell integration into artificial neural networks may enable more robust, generalized, and smarter computers. In this paper we give an overview of grid cell research since their discovery, their role in neuroscience and cognitive science, and possible future directions of artificial intelligence research.
