2 code implementations • 19 Dec 2022 • Taylor Webb, Keith J. Holyoak, Hongjing Lu
In human cognition, this capacity is closely tied to an ability to reason by analogy.
no code implementations • 29 Sep 2022 • Taylor W. Webb, Shuhao Fu, Trevor Bihl, Keith J. Holyoak, Hongjing Lu
Human reasoning is grounded in an ability to identify highly abstract commonalities governing superficially dissimilar visual inputs.
1 code implementation • 3 Sep 2021 • Arjun R. Akula, Keze Wang, Changsong Liu, Sari Saba-Sadiya, Hongjing Lu, Sinisa Todorovic, Joyce Chai, Song-Chun Zhu
More concretely, our CX-ToM framework generates sequence of explanations in a dialog by mediating the differences between the minds of machine and human user.
no code implementations • 14 May 2021 • Nicholas Ichien, Qing Liu, Shuhao Fu, Keith J. Holyoak, Alan Yuille, Hongjing Lu
We compared human performance to that of two recent deep learning models (Siamese Network and Relation Network) directly trained to solve these analogy problems, as well as to that of a compositional model that assesses relational similarity between part-based representations.
no code implementations • 30 Mar 2021 • Hongjing Lu, Nicholas Ichien, Keith J. Holyoak
The human ability to flexibly reason using analogies with domain-general content depends on mechanisms for identifying relations between concepts, and for mapping concepts and their relations across analogs.
no code implementations • 6 Mar 2021 • Xiaofeng Gao, Luyao Yuan, Tianmin Shu, Hongjing Lu, Song-Chun Zhu
Our experiments with human participants demonstrate that a short calibration using REMP can effectively bridge the gap between what a non-expert user thinks a robot can reach and the ground truth.
1 code implementation • NeurIPS 2019 • Chi Zhang, Baoxiong Jia, Feng Gao, Yixin Zhu, Hongjing Lu, Song-Chun Zhu
"Thinking in pictures," [1] i. e., spatial-temporal reasoning, effortless and instantaneous for humans, is believed to be a significant ability to perform logical induction and a crucial factor in the intellectual history of technology development.
no code implementations • 25 Nov 2019 • Mark Edmonds, Xiaojian Ma, Siyuan Qi, Yixin Zhu, Hongjing Lu, Song-Chun Zhu
Given these general theories, the goal is to train an agent by interactively exploring the problem space to (i) discover, form, and transfer useful abstract and structural knowledge, and (ii) induce useful knowledge from the instance-level attributes observed in the environment.
no code implementations • 15 Sep 2019 • Arjun R. Akula, Changsong Liu, Sari Saba-Sadiya, Hongjing Lu, Sinisa Todorovic, Joyce Y. Chai, Song-Chun Zhu
We present a new explainable AI (XAI) framework aimed at increasing justified human trust and reliance in the AI machine through explanations.
Action Recognition
Explainable Artificial Intelligence (XAI)
+2
no code implementations • NeurIPS 2010 • Hongjing Lu, Tungyou Lin, Alan Lee, Luminita Vese, Alan L. Yuille
We then measured human performance for motion tasks and found that we obtained better fit for the L1-norm (Laplace) than for the L2-norm (Gaussian).
no code implementations • NeurIPS 2010 • Shuang Wu, Xuming He, Hongjing Lu, Alan L. Yuille
The human vision system is able to effortlessly perceive both short-range and long-range motion patterns in complex dynamic scenes.
no code implementations • NeurIPS 2009 • Hongjing Lu, Matthew Weiden, Alan L. Yuille
We develop a Bayesian sequential model for category learning.
no code implementations • NeurIPS 2008 • Shuang Wu, Hongjing Lu, Alan L. Yuille
Psychophysical experiments show that humans are better at perceiving rotation and expansion than translation.
no code implementations • NeurIPS 2007 • Hongjing Lu, Alan L. Yuille
We describe a novel noisy-logical distribution for representing the distribution of a binary output variable conditioned on multiple binary input variables.