We present Temporal and Object Quantification Networks (TOQ-Nets), a new class of neuro-symbolic networks with a structural bias that enables them to learn to recognize complex relational-temporal events. This is done by including reasoning layers that implement finite-domain quantification over objects and time. The structure allows them to generalize directly to input instances with varying numbers of objects in temporal sequences of varying lengths. We evaluate TOQ-Nets on input domains that require recognizing event-types in terms of complex temporal relational patterns. We demonstrate that TOQ-Nets can generalize from small amounts of data to scenarios containing more objects than were present during training and to temporal warpings of input sequences.

翻译：我们提出时空和物体量化网络(TOQ-Nets),这是一个新型的神经-体积网络(TOQ-Nets),具有结构性偏差,使他们能够学会识别复杂的关系-时空事件。这包括了对物体和时间进行有限领域量化的推理层。结构允许它们直接向时间序列不同、时间序列长度不同的物体输入实例进行概括。我们评估了需要从复杂的时间关系模式中识别事件类型的输入领域的TOQ-Nets。我们证明,TOQ-Nets可以从少量数据向包含比培训期间更多的物体的假设以及输入序列的时间扭曲情况进行概括。