An official website of the United States government
Abstract The increasing integration of artificial intelligence (AI) in visual analytics (VA) tools raises vital questions about the behavior of users, their trust, and the potential of induced biases when provided with guidance during data exploration. We present an experiment where participants engaged in a visual data exploration task while receiving intelligent suggestions supplemented with four different transparency levels. We also modulated the difficulty of the task (easy or hard) to simulate a more tedious scenario for the analyst. Our results indicate that participants were more inclined to accept suggestions when completing a more difficult task despite theai's lower suggestion accuracy. Moreover, the levels of transparency tested in this study did not significantly affect suggestion usage or subjective trust ratings of the participants. Additionally, we observed that participants who utilized suggestions throughout the task explored a greater quantity and diversity of data points. We discuss these findings and the implications of this research for improving the design and effectiveness ofai‐guidedvatools.
more »
« less
Mixed-Initiative Level Design with RL Brush
This paper introduces RL Brush, a level-editing tool for tile-based games designed for mixed-initiative co-creation. The tool uses reinforcement-learning-based models to augment manual human level-design through the addition of AI-generated suggestions. Here, we apply RL Brush to designing levels for the classic puzzle game Sokoban. We put the tool online and tested it in 39 different sessions. The results show that users using the AI suggestions stay around longer and their created levels on average are more playable and more complex than without.
more »
« less
- Award ID(s):
- 1717324
- PAR ID:
- 10231866
- Date Published:
- Journal Name:
- Artificial Intelligence in Music, Sound, Art and Design - 10th International Conference, EvoMUSART 2021, Held as Part of EvoStar 2021
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Reinforcement learning (RL) can help agents learn complex tasks that would be hard to specify using standard imperative programming. However, end users may have trouble personalizing their technology using RL due to a lack of technical expertise. Prior work has explored means of supporting end users after a problem for the RL agent to solve has been defined. Little work, however, has explored how to support end users when defining this problem. We propose a tool to provide structured support for end users defining problems for RL agents. Through this tool, users can (i) directly and indirectly specify the problem as a Markov decision process (MDP); (ii) receive automatic suggestions on possible MDP changes that would enhance training time and accuracy; and (iii) revise the MDP after training the agent to solve it. We believe this work will help reduce barriers to using RL and contribute to the existing literature on designing human-in-the-loop systems.more » « less
-
Not AvailableModern Artificial Intelligence (AI) workloads demand computing systems with large silicon area to sustain throughput and competitive performance. However, prohibitive manufacturing costs and yield limitations at advanced tech nodes and die-size reaching the reticle limit restrain us from achieving this. With the recent innovations in advanced packaging technologies, chiplet-based architectures have gained significant attention in the AI hardware domain. However, the vast design space of chiplet-based AI accelerator design and the absence of system and package-level co-design methodology make it difficult for the designer to find the optimum design point regarding Power, Performance, Area, and manufacturing Cost (PPAC). This paper presents Chiplet-Gym, a Reinforcement Learning (RL)-based optimization framework to explore the vast design space of chiplet-based AI accelerators, encompassing the resource allocation, placement, and packaging architecture. We analytically model the PPAC of the chiplet-based AI accelerator and integrate it into an OpenAI gym environment to evaluate the design points. We also explore non-RL-based optimization approaches and combine these two approaches to ensure the robustness of the optimizer. The optimizer-suggested design point achieves 1.52× throughput, 0.27× energy, and 0.89× cost of its monolithic counterpart at iso-area.more » « less
-
Research analytics has become an indispensable part in today’s higher education institutions’ organizational structure. It not only provides a mechanism or platform to present research awards and expenditures data to internal and external data users, but also serves a superior tool that enables data-driven strategic decision makings with more reliable, valid, and in-depth analysis. The development of Artificial Intelligence techniques could push the boundary of Research Analytics to an even higher level by incorporating the abundance of data scattered across the university. We propose to present one attempt adopted by University at Albany, State University of New York (UAlbany) to incorporate AI techniques to Research Analytics: a project called Research Highlighter-MatchMaker. The Research Highlighter-MatchMaker project aims to identify research clusters at UAlbany, recommend funding opportunities for faculty/researcher, and suggest potential collaborations. Based on AI and Big Language Models, the project will identify core research clusters by UAlbany faculty and researchers and suggest potential collaborations for multidisciplinary projects across the campus. Moreover, the project aims to recommend more suitable and relevant funding opportunities to different faculty and researchers based on their research track records including their grant proposal abstracts and publication abstracts, with a potential to incorporate more research data associated with researchers such as technology transfer agreements and compliance documents in the future. One major strength of this self-established project is that it takes advantage of AI techniques to provide more personalized and tailored matches for faculty and researchers by considering their research track records on file, instead of providing limited recommendations based on only keyword match that is adopted by many current products on the market. Our purpose is to offer personalized suggestions to faculty and researchers with well-matched funding opportunities, save their time and effort on searching and screening a long list of funding opportunities from databases on their own, and avoid the occurrence of missing good funding opportunities that they could have successfully obtained.more » « less
-
The rise of complex AI systems in healthcare and other sectors has led to a growing area of research called Explainable AI (XAI) designed to increase transparency. In this area, quantitative and qualitative studies focus on improving user trust and task performance by providing system- and prediction-level XAI features. We analyze stakeholder engagement events (interviews and workshops) on the use of AI for kidney transplantation. From this we identify themes which we use to frame a scoping literature review on current XAI features. The stakeholder engagement process lasted over nine months covering three stakeholder group's workflows, determining where AI could intervene and assessing a mock XAI decision support system. Based on the stakeholder engagement, we identify four major themes relevant to designing XAI systems – 1) use of AI predictions, 2) information included in AI predictions, 3) personalization of AI predictions for individual differences, and 4) customizing AI predictions for specific cases. Using these themes, our scoping literature review finds that providing AI predictions before, during, or after decision-making could be beneficial depending on the complexity of the stakeholder's task. Additionally, expert stakeholders like surgeons prefer minimal to no XAI features, AI prediction, and uncertainty estimates for easy use cases. However, almost all stakeholders prefer to have optional XAI features to review when needed, especially in hard-to-predict cases. The literature also suggests that providing both system and prediction-level information is necessary to build the user's mental model of the system appropriately. Although XAI features improve users' trust in the system, human-AI team performance is not always enhanced. Overall, stakeholders prefer to have agency over the XAI interface to control the level of information based on their needs and task complexity. We conclude with suggestions for future research, especially on customizing XAI features based on preferences and tasks.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-030-72914-1_27
