Alabi Adedapo, Vanderelst Dieter, Minai Ali A
Department of Electrical & Computer Engineering, University of Cincinnati, Cincinnati, OH, 45221, USA.
Neural Netw. 2023 Apr;161:116-128. doi: 10.1016/j.neunet.2023.01.010. Epub 2023 Jan 19.
The discovery of place cells and other spatially modulated neurons in the hippocampal complex of rodents has been crucial to elucidating the neural basis of spatial cognition. More recently, the replay of neural sequences encoding previously experienced trajectories has been observed during consummatory behavior-potentially with implications for rapid learning, quick memory consolidation, and behavioral planning. Several promising models for robotic navigation and reinforcement learning have been proposed based on these and previous findings. Most of these models, however, use carefully engineered neural networks, and sometimes require long learning periods. In this paper, we present a self-organizing model incorporating place cells and replay, and demonstrate its utility for rapid one-shot learning in non-trivial environments with obstacles.
在啮齿动物海马复合体中发现位置细胞和其他空间调制神经元对于阐明空间认知的神经基础至关重要。最近，在 consummatory行为期间观察到编码先前经历轨迹的神经序列的回放——这可能对快速学习、快速记忆巩固和行为规划有影响。基于这些以及先前的发现，已经提出了几种用于机器人导航和强化学习的有前景的模型。然而，这些模型中的大多数都使用精心设计的神经网络，并且有时需要很长的学习时间。在本文中，我们提出了一种结合位置细胞和回放的自组织模型，并展示了其在具有障碍物的复杂环境中进行快速一次性学习的效用。
