Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Dodge, Jonathan"'
Autor:
Koujalgi, Sujay, Anderson, Andrew, Adenuga, Iyadunni, Soneji, Shikha, Dikkala, Rupika, Nader, Teresita Guzman, Soccio, Leo, Panda, Sourav, Das, Rupak Kumar, Burnett, Margaret, Dodge, Jonathan
Assessing an AI system's behavior-particularly in Explainable AI Systems-is sometimes done empirically, by measuring people's abilities to predict the agent's next move-but how to perform such measurements? In empirical studies with humans, an obviou
Externí odkaz:
http://arxiv.org/abs/2409.00069
The complexities of legalese in terms and policy documents can bind individuals to contracts they do not fully comprehend, potentially leading to uninformed data sharing. Our work seeks to alleviate this issue by developing language models that provi
Externí odkaz:
http://arxiv.org/abs/2404.13087
The project's aim is to create an AI agent capable of selecting good actions in a game-playing domain called Battlespace. Sequential domains like Battlespace are important testbeds for planning problems, as such, the Department of Defense uses such d
Externí odkaz:
http://arxiv.org/abs/2402.10290
Autor:
Adenuga, Iyadunni, Dodge, Jonathan
We grapple with the question: How, for whom and why should explainable artificial intelligence (XAI) aim to support the user goal of agency? In particular, we analyze the relationship between agency and explanations through a user-centric lens throug
Externí odkaz:
http://arxiv.org/abs/2312.03193
Autor:
Lam, Kin-Ho, Lin, Zhengxian, Irvine, Jed, Dodge, Jonathan, Shureih, Zeyad T, Khanna, Roli, Kahng, Minsuk, Fern, Alan
Enabling humans to identify potential flaws in an agent's decision making is an important Explainable AI application. We consider identifying such flaws in a planning-based deep reinforcement learning (RL) agent for a complex real-time strategy game.
Externí odkaz:
http://arxiv.org/abs/2109.13978
Autor:
Dodge, Jonathan Eldon
We attempted to define target genes that were inactivated in acute myeloid leukemia (AML) by DNA methylation. We hypothesized that hypermethylation of 51 CpG islands is associated with transcriptional silencing of the corresponding gene and participa
Externí odkaz:
http://hdl.handle.net/10150/284143
Autor:
Anderson, Andrew, Dodge, Jonathan, Sadarangani, Amrita, Juozapaitis, Zoe, Newman, Evan, Irvine, Jed, Chattopadhyay, Souti, Fern, Alan, Burnett, Margaret
We present a user study to investigate the impact of explanations on non-experts' understanding of reinforcement learning (RL) agents. We investigate both a common RL visualization, saliency maps (the focus of attention), and a more recent explanatio
Externí odkaz:
http://arxiv.org/abs/1903.09708
Ensuring fairness of machine learning systems is a human-in-the-loop process. It relies on developers, users, and the general public to identify fairness problems and make improvements. To facilitate the process we need effective, unbiased, and user-
Externí odkaz:
http://arxiv.org/abs/1901.07694
Autor:
Penney, Sean, Dodge, Jonathan, Hilderbrand, Claudia, Anderson, Andrew, Simpson, Logan, Burnett, Margaret
Assessing and understanding intelligent agents is a difficult task for users that lack an AI background. A relatively new area, called "Explainable AI," is emerging to help address this problem, but little is known about how users would forage throug
Externí odkaz:
http://arxiv.org/abs/1711.08019
How should an AI-based explanation system explain an agent's complex behavior to ordinary end users who have no background in AI? Answering this question is an active research area, for if an AI-based explanation system could effectively explain inte
Externí odkaz:
http://arxiv.org/abs/1711.06953