10 found
Order:
Disambiguations
Stuart Russell [7]Stuart J. Russell [3]Stuart Jonathan Russell [1]
  1.  19
    Rationality and intelligence.Stuart J. Russell - 1997 - Artificial Intelligence 94 (1-2):57-77.
  2.  25
    Principles of metareasoning.Stuart Russell & Eric Wefald - 1991 - Artificial Intelligence 49 (1-3):361-395.
  3. Rationality and Intelligence: A Brief Update.Stuart Russell - 2016 - In Vincent C. Müller (ed.), Fundamental Issues of Artificial Intelligence. Cham: Springer.
    No categories
     
    Export citation  
     
    Bookmark   7 citations  
  4. A Logical Approach to Reasoning by Analogy.Todd R. Davies & Stuart J. Russell - 1987 - In John P. McDermott (ed.), Proceedings of the 10th International Joint Conference on Artificial Intelligence (IJCAI'87). Morgan Kaufmann Publishers. pp. 264-270.
    We analyze the logical form of the domain knowledge that grounds analogical inferences and generalizations from a single instance. The form of the assumptions which justify analogies is given schematically as the "determination rule", so called because it expresses the relation of one set of variables determining the values of another set. The determination relation is a logical generalization of the different types of dependency relations defined in database theory. Specifically, we define determination as a relation between schemata of first (...)
    Direct download  
     
    Export citation  
     
    Bookmark   7 citations  
  5.  21
    Social Choice for AI Alignment: Dealing with Diverse Human Feedback.Vincent Conitzer, Rachel Freedman, Jobst Heitzig, Wesley H. Holliday, Bob M. Jacobs, Nathan Lambert, Milan Mosse, Eric Pacuit, Stuart Russell, Hailey Schoelkopf, Emanuel Tewolde & William S. Zwicker - manuscript
    Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, so that, for example, they refuse to comply with requests for help with committing crimes or with producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans' expressed preferences over multiple outputs. Another approach is constitutional AI, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How (...)
    Direct download  
     
    Export citation  
     
    Bookmark  
  6.  17
    Optimal composition of real-time systems.Shlomo Zilberstein & Stuart Russell - 1996 - Artificial Intelligence 82 (1-2):181-213.
  7.  77
    Generative AI models should include detection mechanisms as a condition for public release.Alistair Knott, Dino Pedreschi, Raja Chatila, Tapabrata Chakraborti, Susan Leavy, Ricardo Baeza-Yates, David Eyers, Andrew Trotman, Paul D. Teal, Przemyslaw Biecek, Stuart Russell & Yoshua Bengio - 2023 - Ethics and Information Technology 25 (4):1-7.
    The new wave of ‘foundation models’—general-purpose generative AI models, for production of text (e.g., ChatGPT) or images (e.g., MidJourney)—represent a dramatic advance in the state of the art for AI. But their use also introduces a range of new risks, which has prompted an ongoing conversation about possible regulatory mechanisms. Here we propose a specific principle that should be incorporated into legislation: that any organization developing a foundation model intended for public use must demonstrate a reliable detection mechanism for the (...)
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark  
  8.  91
    Inductive learning by machines.Stuart Russell - 1991 - Philosophical Studies 64 (October):37-64.
  9.  8
    Object identification: a Bayesian analysis with application to traffic surveillance.Timothy Huang & Stuart Russell - 1998 - Artificial Intelligence 103 (1-2):77-93.
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark  
  10.  32
    Rationality as an explanation of language?Stuart J. Russell - 1987 - Behavioral and Brain Sciences 10 (4):730.