paper-with-me

홈 › Papers

The Challenge of Crafting Intelligible Intelligence

2018-03-09 · Daniel S. Weld, Gagan Bansal

Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to understand. Yet organizations are deploying AI algorithms in many mission-critical settings. To trust their behavior, we must make AI intelligible, either by using inherently interpretable models or by developing new methods for explaining and controlling otherwise overwhelmingly complex decisions using local approximation, vocabulary alignment, and interactive explanation. This paper argues that intelligibility is essential, surveys recent work on building such systems, and highlights key directions for research.

📄 PDF Abstract BibTeX arXiv:1803.04263

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

What Makes a Message Persuasive? Identifying Adaptations Towards Persuasiveness in Nine Exploratory Case Studies

2021-04-26 · Sebastian Duerr, Krystian Teodor Lange, Peter A. Gloor

The ability to persuade others is critical to professional and personal success. However, crafting persuasive messages is demanding and poses various challenges. We conducted nine exploratory case studies to identify ada…

PersuasivenessText Generation

A Review of Explainable Artificial Intelligence in Manufacturing

2021-07-05 · Georgios Sofianidis, Jože M. Rožanec, Dunja Mladenić, Dimosthenis Kyriazis

The implementation of Artificial Intelligence (AI) systems in the manufacturing domain enables higher production efficiency, outstanding performance, and safer operations, leveraging powerful tools such as deep learning …

Decision MakingExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)reinforcement-learning+1

Making AI Intelligible: Philosophical Foundations

2024-06-12 · Herman Cappelen, Josh Dever

Can humans and artificial intelligences share concepts and communicate? 'Making AI Intelligible' shows that philosophical work on the metaphysics of meaning can help answer these questions. Herman Cappelen and Josh Dever…

Philosophy

Human in the AI loop via xAI and Active Learning for Visual Inspection

2023-07-03 · Jože M. Rožanec, Elias Montini, Vincenzo Cutrona, Dimitrios Papamartzivanos 외

Industrial revolutions have historically disrupted manufacturing by introducing automation into production. Increasing automation reshapes the role of the human worker. Advances in robotics and artificial intelligence op…

Active LearningExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)

Disturbing Reinforcement Learning Agents with Corrupted Rewards

2021-02-12 · Rubén Majadas, Javier García, Fernando Fernández

Reinforcement Learning (RL) algorithms have led to recent successes in solving complex games, such as Atari or Starcraft, and to a huge impact in real-world applications, such as cybersecurity or autonomous driving. In t…

Autonomous Drivingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1