路径整合与物体-位置绑定在动作条件预测序列网络中出现
Path Integration and Object-Location Binding Emerge in an Action-Conditioned Predictive Sequence Network
AI总结：
研究探讨了动作条件预测序列网络如何通过上下文学习提升预测准确性，并揭示了路径整合和动态绑定在结构化表示中的作用。
摘要：
适应性认知需要结构化的物体及其关系内部模型。预测神经网络常被提议用于学习此类世界模型，但其如何实例化以及如何支持预测仍不清楚。我们在一个最小的计算机模拟环境中进行了研究。循环神经网络按顺序从二维连续标记场景中采样标记，并训练其根据当前输入和类似扫视的位移预测下一个标记。在新场景中，预测准确性在序列中逐步提高，表明了上下文学习。解码分析揭示了路径整合和动态标记身份与位置的绑定。干预分析显示，新的绑定可以在序列后期学习，且超出分布的绑定也可以学习。这些发现表明，依赖于灵活绑定的结构化表示如何出现以支持预测，为认知科学相关的序列世界建模提供了机制解释。
英文摘要：
Adaptive cognition requires structured internal models of objects and their relations. Predictive neural networks are often proposed to learn such world models, but how these are instantiated and how they support prediction remain unclear. We investigate this in a minimal in-silico setting. A recurrent neural network samples tokens sequentially from 2D continuous token scenes and is trained to predict the upcoming token from the current input and a saccade-like displacement. On novel scenes, prediction accuracy improves across the sequence, indicating in-context learning. Decoding analyses reveal path integration and dynamic binding of token identity to position. Interventional analyses show that new bindings can be learned late in sequence and that out-of-distribution bindings can be learned as well. Together, these findings show how structured representations relying on flexible binding emerge to support prediction, offering a mechanistic account of sequential world modeling relevant to cognitive science.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
