Zobrazeno 1 - 10
of 371
pro vyhledávání: '"Scheutz, Matthias"'
Autor:
Goel, Shivam, Wei, Yichen, Lymperopoulos, Panagiotis, Chura, Klara, Scheutz, Matthias, Sinapov, Jivko
As AI agents leave the lab and venture into the real world as autonomous vehicles, delivery robots, and cooking robots, it is increasingly necessary to design and comprehensively evaluate algorithms that tackle the ``open-world''. To this end, we int
Externí odkaz:
http://arxiv.org/abs/2401.03546
Domain generalization aims to learn a model with good generalization ability, that is, the learned model should not only perform well on several seen domains but also on unseen domains with different data distributions. State-of-the-art domain genera
Externí odkaz:
http://arxiv.org/abs/2304.00629
Autor:
Thai, Tung, Shen, Ming, Garg, Mayank, Kalani, Ayush, Vaidya, Nakul, Soni, Utkarsh, Verma, Mudit, Gopalakrishnan, Sriram, Varshney, Neeraj, Baral, Chitta, Kambhampati, Subbarao, Sinapov, Jivko, Scheutz, Matthias
Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to be able to guarantee satisfactory task performance. Certain novelties (e.g., changes in environment dynamics) can
Externí odkaz:
http://arxiv.org/abs/2302.14208
Publikováno v:
International Conference on Machine Learning and Applications (ICMLA-2022)
Domain generalization (DG) is a branch of transfer learning that aims to train the learning models on several seen domains and subsequently apply these pre-trained models to other unseen (unknown but related) domains. To deal with challenging setting
Externí odkaz:
http://arxiv.org/abs/2210.15000
In this paper, we propose a novel domain generalization (DG) framework based on a new upper bound to the risk on the unseen domain. Particularly, our framework proposes to jointly minimize both the covariate-shift as well as the concept-shift between
Externí odkaz:
http://arxiv.org/abs/2208.00898
We propose RAPid-Learn: Learning to Recover and Plan Again, a hybrid planning and learning method, to tackle the problem of adapting to sudden and unexpected changes in an agent's environment (i.e., novelties). RAPid-Learn is designed to formulate an
Externí odkaz:
http://arxiv.org/abs/2206.12493
Autor:
Feeney, Patrick, Schneider, Sarah, Lymperopoulos, Panagiotis, Liu, Li-Ping, Scheutz, Matthias, Hughes, Michael C.
In order for artificial agents to successfully perform tasks in changing environments, they must be able to both detect and adapt to novelty. However, visual novelty detection research often only evaluates on repurposed datasets such as CIFAR-10 orig
Externí odkaz:
http://arxiv.org/abs/2206.11736
As AI-enabled robots enter the realm of healthcare and caregiving, it is important to consider how they will address the dimensions of care and how they will interact not just with the direct receivers of assistance, but also with those who provide i
Externí odkaz:
http://arxiv.org/abs/2206.00776
Invariance-principle-based methods such as Invariant Risk Minimization (IRM), have recently emerged as promising approaches for Domain Generalization (DG). Despite promising theory, such approaches fail in common classification tasks due to the mixin
Externí odkaz:
http://arxiv.org/abs/2201.10460
Autor:
Goel, Shivam, Lymperopoulos, Panagiotis, Thielstrom, Ravenna, Krause, Evan, Feeney, Patrick, Lorang, Pierrick, Schneider, Sarah, Wei, Yichen, Kildebeck, Eric, Goss, Stephen, Hughes, Michael C., Liu, Liping, Sinapov, Jivko, Scheutz, Matthias
Publikováno v:
In Artificial Intelligence June 2024 331