Temporal and Object Quantification Networks
Author(s)
Mao, Jiayuan; Luo, Zhezheng; Gan, Chuang; Tenenbaum, Joshua B; Wu, Jiajun; Kaelbling, Leslie Pack; Ullman, Tomer D; ... Show more Show less
DownloadAccepted version (1.650Mb)
Open Access Policy
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
<jats:p>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.</jats:p>
Date issued
2021Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; MIT-IBM Watson AI LabJournal
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Publisher
International Joint Conferences on Artificial Intelligence
Citation
Mao, Jiayuan, Luo, Zhezheng, Gan, Chuang, Tenenbaum, Joshua B, Wu, Jiajun et al. 2021. "Temporal and Object Quantification Networks." Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence.
Version: Author's final manuscript