一种基于上下文维护和检索记忆的神经网络
A neural network that maintains and retrieves memories based on context
- University of Texas at Austin（德克萨斯大学奥斯汀分校）
- Washington University in St. Louis（圣路易斯华盛顿大学）
- City University of Hong Kong（香港城市大学）
- University of Chicago（芝加哥大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究训练带有情景记忆缓冲区的循环神经网络，通过贝叶斯推断上下文并低秩调节连接，使模型在自然电影观看中更贴近人脑活动，并加速上下文一致的记忆检索。
AI中文摘要：
每天，人们都在不断推断情境上下文，并调整他们理解和记忆世界的方式。由前额叶皮层发出信号的上下文，已知能够调节工作记忆和情景记忆，但对此调节机制的算法理解仍然有限。在此，我们训练了一个带有情景记忆缓冲区的循环神经网络（RNN），在观看自然电影时，通过贝叶斯推断来推断上下文，同时不断预测即将出现的场景。当推断出的上下文以低秩方式调节RNN的循环连接（工作记忆的基础）时，模型的活动模式与在功能性磁共振成像（fMRI）中观看相同电影的人类参与者的神经反应最为匹配。上下文还调节情景记忆的检索，使得模型不仅基于内容相似性，还基于上下文相似性来检索记忆。这是通过带有自注意力的键值系统实现的，该系统设计用于额外编码上下文并检索与上下文一致的记忆。由此产生的模型不仅更接近人脑表征，而且学习像人类一样检索记忆的速度远快于没有上下文调节的模型。总之，我们的发现提出了一种计算机制，通过该机制，上下文在自然环境中调节信息维护和长期记忆检索。
英文摘要：
Every day, people continuously infer situational context and adjust the way they understand and remember the world. Context, signaled by the prefrontal cortex, is known to modulate working memory and episodic memory, but the algorithmic understanding of this modulation remains limited. Here, we train a recurrent neural network (RNN), augmented with an episodic memory buffer, to infer context using Bayesian inference as it continuously makes predictions of upcoming scenes while watching naturalistic movies. When the inferred context modulates the RNN's recurrent connectivity (the basis of working memory) in a low-rank manner, the model's activity patterns best match neural responses in human participants who watched the same movies during fMRI. Context also modulates episodic memory retrieval, such that the model retrieves memories based on not only content similarity but also context similarity. This is implemented as a key-value system with self-attention, designed to additionally encode context and retrieve context-congruent memories. The resulting model not only better resembles human brain representations but also learns to retrieve memories like humans much faster than a model without context modulation. Together, our findings suggest a computational mechanism by which context modulates information maintenance and long-term memory retrieval in naturalistic environments.
