Temporal and Object Quantification Networks
<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 quantific...
Main Authors: | Mao, Jiayuan (Author), Luo, Zhezheng (Author), Gan, Chuang (Author), Tenenbaum, Joshua B (Author), Wu, Jiajun (Author), Kaelbling, Leslie Pack (Author), Ullman, Tomer D (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
International Joint Conferences on Artificial Intelligence,
2022-07-15T17:22:16Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Combining physical simulators and object-based networks for control
by: Ajay, Anurag, et al.
Published: (2020) -
The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision
by: Mao, Jiayuan, et al.
Published: (2020) -
Visual concept-metaconcept learning
by: Han, Chi, et al.
Published: (2021) -
Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks
by: Silver, Tom, et al.
Published: (2022) -
A Compositional Object-Based Approach to Learning Physical Dynamics
by: Chang, Michael B., et al.
Published: (2017)