Structured Event Memory: A Neuro-Symbolic Model of Event Cognition
Structured Event Memory: A Neuro-Symbolic Model of Event Cognition
复制标题
DOI：
10.1037/rev0000177
复制
发表时间：
2020-04-01
影响因子：
5.4
通讯作者：
Gershman, Samuel J.
中科院分区：
文献类型：
--
作者：
Franklin, Nicholas T.;Norman, Kenneth A.;Gershman, Samuel J.
人类自发地将连续的经历组织成离散的事件，并使用这些事件的学习结构来概括和组织记忆。我们介绍了事件认知的结构化事件记忆（SEM）模型，该模型解释了人类在事件分割、记忆和泛化方面的能力。SEM是来自一个概率生成模型的事件动态定义在结构化的符号场景。通过在向量空间中嵌入符号场景表示，并在这个连续空间中参数化场景动态，SEM结合了结构化和神经网络方法的优势，以实现高级认知。在这个生成模型上使用概率推理，SEM可以推断事件边界，学习事件图式，并使用事件知识来重建过去的经验。我们表明，SEM可以扩展到高维输入空间，产生类似人类的事件分割自然的视频数据，并占了广泛的记忆现象。
Humans spontaneously organize a continuous experience into discrete events and use the learned structure of these events to generalize and organize memory. We introduce the Structured Event Memory (SEM) model of event cognition, which accounts for human abilities in event segmentation, memory, and generalization. SEM is derived from a probabilistic generative model of event dynamics defined over structured symbolic scenes. By embedding symbolic scene representations in a vector space and parametrizing the scene dynamics in this continuous space, SEM combines the advantages of structured and neural network approaches to high-level cognition. Using probabilistic reasoning over this generative model, SEM can infer event boundaries, learn event schemata, and use event knowledge to reconstruct past experience. We show that SEM can scale up to highdimensional input spaces, producing human- like event segmentation for naturalistic video data, and accounts for a wide array of memory phenomena.