21 found
Order:
  1. Building machines that learn and think like people.Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum & Samuel J. Gershman - 2017 - Behavioral and Brain Sciences 40.
    Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats that of humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking (...)
    No categories
    Direct download (6 more)  
     
    Export citation  
     
    Bookmark   98 citations  
  2.  18
    A theory of learning to infer.Ishita Dasgupta, Eric Schulz, Joshua B. Tenenbaum & Samuel J. Gershman - 2020 - Psychological Review 127 (3):412-441.
    No categories
    Direct download (3 more)  
     
    Export citation  
     
    Bookmark   12 citations  
  3.  23
    Structured Event Memory: A neuro-symbolic model of event cognition.Nicholas T. Franklin, Kenneth A. Norman, Charan Ranganath, Jeffrey M. Zacks & Samuel J. Gershman - 2020 - Psychological Review 127 (3):327-361.
    No categories
    Direct download (3 more)  
     
    Export citation  
     
    Bookmark   10 citations  
  4.  40
    Moral dynamics: Grounding moral judgment in intuitive physics and intuitive psychology.Felix A. Sosa, Tomer Ullman, Joshua B. Tenenbaum, Samuel J. Gershman & Tobias Gerstenberg - 2021 - Cognition 217 (C):104890.
  5.  34
    Context, learning, and extinction.Samuel J. Gershman, David M. Blei & Yael Niv - 2010 - Psychological Review 117 (1):197-209.
  6.  15
    Deconstructing the human algorithms for exploration.Samuel J. Gershman - 2018 - Cognition 173 (C):34-42.
    No categories
    Direct download (3 more)  
     
    Export citation  
     
    Bookmark   10 citations  
  7.  27
    Remembrance of inferences past: Amortization in human hypothesis generation.Ishita Dasgupta, Eric Schulz, Noah D. Goodman & Samuel J. Gershman - 2018 - Cognition 178 (C):67-81.
    No categories
    Direct download (3 more)  
     
    Export citation  
     
    Bookmark   6 citations  
  8.  17
    Heuristics from bounded meta-learned inference.Marcel Binz, Samuel J. Gershman, Eric Schulz & Dominik Endres - 2022 - Psychological Review 129 (5):1042-1077.
    Direct download (3 more)  
     
    Export citation  
     
    Bookmark   2 citations  
  9.  77
    Introduction to Progress and Puzzles of Cognitive Science.Rick Dale, Ruth M. J. Byrne, Emma Cohen, Ophelia Deroy, Samuel J. Gershman, Janet H. Hsiao, Ping Li, Padraic Monaghan, David C. Noelle, Iris van Rooij, Priti Shah, Michael J. Spivey & Sashank Varma - 2024 - Cognitive Science 48 (7):e13480.
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark  
  10.  26
    Origin of perseveration in the trade-off between reward and complexity.Samuel J. Gershman - 2020 - Cognition 204 (C):104394.
    No categories
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark   3 citations  
  11.  22
    Actual and counterfactual effort contribute to responsibility attributions in collaborative tasks.Yang Xiang, Jenna Landy, Fiery A. Cushman, Natalia Vélez & Samuel J. Gershman - 2023 - Cognition 241 (C):105609.
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark   1 citation  
  12.  37
    Explaining compound generalization in associative and causal learning through rational principles of dimensional generalization.Fabian A. Soto, Samuel J. Gershman & Yael Niv - 2014 - Psychological Review 121 (3):526-558.
  13.  24
    Learning the Structure of Social Influence.Samuel J. Gershman, Hillard Thomas Pouncy & Hyowon Gweon - 2017 - Cognitive Science 41 (S3):545-575.
    We routinely observe others’ choices and use them to guide our own. Whose choices influence us more, and why? Prior work has focused on the effect of perceived similarity between two individuals, such as the degree of overlap in past choices or explicitly recognizable group affiliations. In the real world, however, any dyadic relationship is part of a more complex social structure involving multiple social groups that are not directly observable. Here we suggest that human learners go beyond dyadic similarities (...)
    No categories
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark   4 citations  
  14.  21
    Decision by sampling implements efficient coding of psychoeconomic functions.Rahul Bhui & Samuel J. Gershman - 2018 - Psychological Review 125 (6):985-1001.
    No categories
    Direct download (3 more)  
     
    Export citation  
     
    Bookmark   3 citations  
  15.  72
    Novelty and Inductive Generalization in Human Reinforcement Learning.Samuel J. Gershman & Yael Niv - 2015 - Topics in Cognitive Science 7 (3):391-415.
    In reinforcement learning, a decision maker searching for the most rewarding option is often faced with the question: What is the value of an option that has never been tried before? One way to frame this question is as an inductive problem: How can I generalize my previous experience with one set of options to a novel option? We show how hierarchical Bayesian inference can be used to solve this problem, and we describe an equivalence between the Bayesian model and (...)
    Direct download (4 more)  
     
    Export citation  
     
    Bookmark   3 citations  
  16.  19
    What Is the Model in Model‐Based Planning?Thomas Pouncy, Pedro Tsividis & Samuel J. Gershman - 2021 - Cognitive Science 45 (1):e12928.
    Flexibility is one of the hallmarks of human problem‐solving. In everyday life, people adapt to changes in common tasks with little to no additional training. Much of the existing work on flexibility in human problem‐solving has focused on how people adapt to tasks in new domains by drawing on solutions from previously learned domains. In real‐world tasks, however, humans must generalize across a wide range of within‐domain variation. In this work we argue that representational abstraction plays an important role in (...)
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark   1 citation  
  17.  20
    Analyzing Machine‐Learned Representations: A Natural Language Case Study.Ishita Dasgupta, Demi Guo, Samuel J. Gershman & Noah D. Goodman - 2020 - Cognitive Science 44 (12):e12925.
    As modern deep networks become more complex, and get closer to human‐like capabilities in certain domains, the question arises as to how the representations and decision rules they learn compare to the ones in humans. In this work, we study representations of sentences in one such artificial system for natural language processing. We first present a diagnostic test dataset to examine the degree of abstract composable structure represented. Analyzing performance on these diagnostic tests indicates a lack of systematicity in representations (...)
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark   1 citation  
  18.  7
    A Hierarchical Bayesian Model of Adaptive Teaching.Alicia M. Chen, Andrew Palacci, Natalia Vélez, Robert D. Hawkins & Samuel J. Gershman - 2024 - Cognitive Science 48 (7):e13477.
    How do teachers learn about what learners already know? How do learners aid teachers by providing them with information about their background knowledge and what they find confusing? We formalize this collaborative reasoning process using a hierarchical Bayesian model of pedagogy. We then evaluate this model in two online behavioral experiments (N = 312 adults). In Experiment 1, we show that teachers select examples that account for learners' background knowledge, and adjust their examples based on learners' feedback. In Experiment 2, (...)
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark  
  19.  39
    Ingredients of intelligence: From classic debates to an engineering roadmap.Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum & Samuel J. Gershman - 2017 - Behavioral and Brain Sciences 40:e281.
    We were encouraged by the broad enthusiasm for building machines that learn and think in more human-like ways. Many commentators saw our set of key ingredients as helpful, but there was disagreement regarding the origin and structure of those ingredients. Our response covers three main dimensions of this disagreement: nature versus nurture, coherent theories versus theory fragments, and symbolic versus sub-symbolic representations. These dimensions align with classic debates in artificial intelligence and cognitive science, although, rather than embracing these debates, we (...)
    No categories
    Direct download (2 more)  
     
    Export citation  
     
    Bookmark   1 citation  
  20.  13
    A probabilistic successor representation for context-dependent learning.Jesse P. Geerts, Samuel J. Gershman, Neil Burgess & Kimberly L. Stachenfeld - 2024 - Psychological Review 131 (2):578-597.
    Direct download (3 more)  
     
    Export citation  
     
    Bookmark  
  21.  32
    Bayesian belief updating after a replication experiment.Alex O. Holcombe & Samuel J. Gershman - 2018 - Behavioral and Brain Sciences 41.