预测性关联记忆：通过时间共现超越相似性进行检索
Predictive Associative Memory: Retrieval Beyond Similarity Through Temporal Co-occurrence
AI总结：
本文提出预测性关联记忆(PAM)，通过时间共现学习嵌入空间的关联结构，实现超越相似性的检索，实验显示其在关联召回和区分能力上表现优异。
摘要：
当前神经系统中的记忆方法依赖于基于相似性的检索：给定一个查询，找到最相似的存储状态。这一假设——有用的记忆是相似的记忆——未能捕捉到生物记忆的基本特性：通过时间共现的关联。我们提出预测性关联记忆(PAM)，其架构中一个JEPA风格的预测器，通过连续经验流中的时间共现训练，学习导航嵌入空间的关联结构。我们引入一个向内JEPA，操作于存储的经验（预测可关联到达的过去状态）作为标准向外JEPA（操作于输入感官数据，预测未来状态）的补充。我们评估PAM作为关联回忆系统——测试回忆的忠实度对于经历的关联——而不是作为检索系统评估在未见关联上的泛化能力。在合成基准上，预测器的顶级检索是真正的时空关联97%的时间（关联精度@1=0.970）；它在跨边界召回@20=0.421，其中余弦相似度得分为零；并且它能够区分经历在一起和从未经历在一起的状态，具有判别AUC为0.916（余弦：0.789）。即使限制在跨房间对，其中嵌入相似性无信息，预测器也达到AUC=0.849（余弦：0.503，机会）。时间洗牌控制确认信号是真实的时空共现结构，而不是嵌入几何：洗牌使跨边界召回降低90%，在训练种子中重复。所有结果在种子（SD < 0.006）和查询选择（SD ≤ 0.012）上均稳定。
英文摘要：
Current approaches to memory in neural systems rely on similarity-based retrieval: given a query, find the most representationally similar stored state. This assumption -- that useful memories are similar memories -- fails to capture a fundamental property of biological memory: association through temporal co-occurrence. We propose Predictive Associative Memory (PAM), an architecture in which a JEPA-style predictor, trained on temporal co-occurrence within a continuous experience stream, learns to navigate the associative structure of an embedding space. We introduce an Inward JEPA that operates over stored experience (predicting associatively reachable past states) as the complement to the standard Outward JEPA that operates over incoming sensory data (predicting future states). We evaluate PAM as an associative recall system -- testing faithfulness of recall for experienced associations -- rather than as a retrieval system evaluated on generalisation to unseen associations. On a synthetic benchmark, the predictor's top retrieval is a true temporal associate 97% of the time (Association Precision@1 = 0.970); it achieves cross-boundary Recall@20 = 0.421 where cosine similarity scores zero; and it separates experienced-together from never-experienced-together states with a discrimination AUC of 0.916 (cosine: 0.789). Even restricted to cross-room pairs where embedding similarity is uninformative, the predictor achieves AUC = 0.849 (cosine: 0.503, chance). A temporal shuffle control confirms the signal is genuine temporal co-occurrence structure, not embedding geometry: shuffling collapses cross-boundary recall by 90%, replicated across training seeds. All results are stable across seeds (SD < 0.006) and query selections (SD $\leq$ 0.012).
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。
