---
title: "Temporal and Object Quantification Networks"
authors:
  - "Jiayuan Mao"
  - "Zhezheng Luo"
  - "Chuang Gan"
  - "Joshua B. Tenenbaum"
  - "Jiajun Wu"
  - "Leslie Pack Kaelbling"
  - "Tomer D. Ullman"
doi: "10.24963/ijcai.2021/386"
url: "https://ijcai.org/proceedings/2021/386"
pdf: "https://ijcai.org/proceedings/2021/0386.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "2804-2811"
track: "Main Track"
keywords:
  - "Machine Learning: Relational Learning"
  - "Machine Learning: Neuro-Symbolic Methods"
---

# Temporal and Object Quantification Networks

Jiayuan Mao, Zhezheng Luo, Chuang Gan, Joshua B. Tenenbaum, Jiajun Wu, Leslie Pack Kaelbling, Tomer D. Ullman

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 2804-2811. DOI: [10.24963/ijcai.2021/386](https://doi.org/10.24963/ijcai.2021/386)

## Abstract

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.