no code implementations • 15 Mar 2024 • Scott Cheng-Hsin Yang, Baxter Eaves, Michael Schmidt, Ken Swanson, Patrick Shafto
Many metrics exist for evaluating the quality of synthetic tabular data; however, we lack an objective, coherent interpretation of the many metrics.
no code implementations • 5 Jun 2023 • Xiaoran Hao, Patrick Shafto
Variational auto-encoders are powerful probabilistic models in generative tasks but suffer from generating low-quality samples which are caused by the holes in the prior.
no code implementations • 26 May 2022 • Pushpi Paranamana, Pei Wang, Patrick Shafto
Evolution of beliefs of a society are a product of interactions between people (horizontal transmission) in the society over generations (vertical transmission).
no code implementations • 17 May 2022 • Scott Cheng-Hsin Yang, Tomas Folke, Patrick Shafto
The goal of explainable Artificial Intelligence (XAI) is to generate human-interpretable explanations, but there are no computationally precise theories of how humans interpret AI generated explanations.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 14 Mar 2022 • Chi-Ken Lu, Patrick Shafto
With Bochner's theorem, DGP with squared exponential kernel can be viewed as a deep trigonometric network consisting of the random feature layers, sine and cosine activation units, and random weight layers.
no code implementations • 17 Dec 2021 • Wei-Ting Chiu, Pei Wang, Patrick Shafto
Optimal transport (OT) formalizes the problem of finding an optimal coupling between probability measures given a cost matrix.
1 code implementation • 1 Oct 2021 • Chi-Ken Lu, Patrick Shafto
Preliminary extrapolation results demonstrate expressive power from the depth of hierarchy by exploiting the exact covariance and hyperdata learning, in comparison with GP kernel composition, DGP variational inference and deep kernel learning.
no code implementations • 16 Jun 2021 • Tomas Folke, ZhaoBin Li, Ravi B. Sojitra, Scott Cheng-Hsin Yang, Patrick Shafto
Adversarial images highlight how vulnerable modern image classifiers are to perturbations outside of their training set.
no code implementations • 8 Jun 2021 • Tomas Folke, Scott Cheng-Hsin Yang, Sean Anderson, Patrick Shafto
Limited expert time is a key bottleneck in medical imaging.
no code implementations • 16 May 2021 • Scott Cheng-Hsin Yang, Tomas Folke, Patrick Shafto
Bayesian Teaching formalizes explanation as a communication act of an explainer to shift the beliefs of an explainee.
no code implementations • 16 Feb 2021 • Junqi Wang, Pei Wang, Patrick Shafto
Obtaining solutions to Optimal Transportation (OT) problems is typically intractable when the marginal spaces are continuous.
no code implementations • 15 Feb 2021 • Arash Givchi, Pei Wang, Junqi Wang, Patrick Shafto
We consider constrained policy optimization in Reinforcement Learning, where the constraints are in form of marginals on state visitations and global action executions.
1 code implementation • 13 Feb 2021 • Khanh Nguyen, Dipendra Misra, Robert Schapire, Miro Dudík, Patrick Shafto
We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities.
General Reinforcement Learning Grounded language learning +2
1 code implementation • 7 Feb 2021 • Scott Cheng-Hsin Yang, Wai Keen Vong, Ravi B. Sojitra, Tomas Folke, Patrick Shafto
State-of-the-art deep-learning systems use decision rules that are challenging for humans to model.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1
no code implementations • NeurIPS Workshop TDA_and_Beyond 2020 • Pei Wang, Arash Givchi, Patrick Shafto
We consider the problem of learning a manifold from a teacher's demonstration.
no code implementations • ICML 2020 • Junqi Wang, Pei Wang, Patrick Shafto
We seek foundational theoretical results for cooperative inference by Bayesian agents through sequential data.
1 code implementation • 7 Feb 2020 • Chi-Ken Lu, Patrick Shafto
Recently, [1] pointed out that the hierarchical structure of DGP well suited modeling the multi-fidelity regression, in which one is provided sparse observations with high precision and plenty of low fidelity observations.
no code implementations • 10 Oct 2019 • Pei Wang, Arash Givchi, Patrick Shafto
We consider the problem of learning a manifold from a teacher's demonstration.
no code implementations • NeurIPS 2020 • Pei Wang, Junqi Wang, Pushpi Paranamana, Patrick Shafto
Cooperative communication plays a central role in theories of human cognition, language, development, culture, and human-robot interaction.
no code implementations • 27 May 2019 • Chi-Ken Lu, Scott Cheng-Hsin Yang, Xiaoran Hao, Patrick Shafto
We propose interpretable DGP based on approximating DGP as a GP by calculating the exact moments, which additionally identify the heavy-tailed nature of some DGP distributions.
no code implementations • 4 Oct 2018 • Pei Wang, Pushpi Paranamana, Patrick Shafto
Cooperation information sharing is important to theories of human learning and has potential implications for machine learning.
1 code implementation • 9 Mar 2018 • Chi-Ken Lu, Scott Cheng-Hsin Yang, Patrick Shafto
We propose a Standing Wave Decomposition (SWD) approximation to Gaussian Process regression (GP).
no code implementations • 24 May 2017 • Scott Cheng-Hsin Yang, Yue Yu, Arash Givchi, Pei Wang, Wai Keen Vong, Patrick Shafto
Cooperative transmission of data fosters rapid accumulation of knowledge by efficiently combining experiences across learners.
no code implementations • 29 Aug 2016 • Olfa Nasraoui, Patrick Shafto
In this paper, we present a preliminary theoretical model and analysis of the mutual interaction between humans and algorithms, based on an iterated learning framework that is inspired from the study of human language evolution.
no code implementations • 1 Jun 2016 • Baxter S. Eaves Jr., Naomi H. Feldman, Thomas L. Griffiths, Patrick Shafto
We qualitatively compare the simulated teaching data with human IDS, finding that the teaching data exhibit many features of IDS, including some that have been taken as evidence IDS is not for teaching.
no code implementations • 25 May 2016 • Baxter S. Eaves Jr, Patrick Shafto
We propose an approach based on human teaching where the problem is formalized as selecting a small subset of the data that will, with high probability, lead the human user to the correct inference.
1 code implementation • 3 Dec 2015 • Vikash Mansinghka, Patrick Shafto, Eric Jonas, Cap Petschulat, Max Gasner, Joshua B. Tenenbaum
CrossCat infers multiple non-overlapping views of the data, each consisting of a subset of the variables, and uses a separate nonparametric mixture to model each view.