Behavioral and Brain Sciences 40 (2017)
AbstractRecent 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 machines will have to reach beyond current engineering trends in both what they learn and how they learn it. Specifically, we argue that these machines should build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; ground learning in intuitive theories of physics and psychology to support and enrich the knowledge that is learned; and harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes toward these goals that can combine the strengths of recent neural network advances with more structured cognitive models.
Added to PP
Historical graph of downloads
References found in this work
Connectionism and Cognitive Architecture: A Critical Analysis.Jerry A. Fodor & Zenon W. Pylyshyn - 1988 - Cognition 28 (1-2):3-71.
Citations of this work
Book: Cognitive Design for Artificial Minds.Antonio Lieto - 2021 - London, UK: Routledge, Taylor & Francis Ltd.
Solving the Black Box Problem: A Normative Framework for Explainable Artificial Intelligence.Carlos Zednik - 2019 - Philosophy and Technology 34 (2):265-288.
Empiricism Without Magic: Transformational Abstraction in Deep Convolutional Neural Networks.Cameron Buckner - 2018 - Synthese (12):1-34.
Similar books and articles
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.
Evidence From Machines That Learn and Think Like People.Kenneth D. Forbus & Dedre Gentner - 2017 - Behavioral and Brain Sciences 40.
Fundamental Issues in Social Robotics.Brian R. Duffy - 2006 - International Review of Information Ethics 6 (12):2006.
'You Gotta Listen to How People Talk': Machines and Natural Language.Jacob Berger & Kyle Ferguson - 2009 - In Richard Brown & Kevin S. Decker (eds.), Terminator and Philosophy: I'll be Back, Therefore I Am. pp. 239-252.
Can Machines Think? An Old Question Reformulated.Achim Hoffmann - 2010 - Minds and Machines 20 (2):203-212.
Expanding Young People's Capacity to Learn.Guy Claxton - 2007 - British Journal of Educational Studies 55 (2):115-134.
Building Machines That Learn and Think for Themselves.Matthew Botvinick, David G. T. Barrett, Peter Battaglia, Nando de Freitas, Darshan Kumaran, Joel Z. Leibo, Timothy Lillicrap, Joseph Modayil, Shakir Mohamed, Neil C. Rabinowitz, Danilo J. Rezende, Adam Santoro, Tom Schaul, Christopher Summerfield, Greg Wayne, Theophane Weber, Daan Wierstra, Shane Legg & Demis Hassabis - 2017 - Behavioral and Brain Sciences 40.
Would You Mind Being Watched by Machines? Privacy Concerns in Data Mining.Vincent C. Müller - 2009 - AI and Society 23 (4):529-544.
Man & Machine: I Wonder If We Can Coexist. [REVIEW]John Durkin - 2003 - AI and Society 17 (3-4):383-390.
Moral Machines:Teaching Robots Right From Wrong: Teaching Robots Right From Wrong.Wendell Wallach & Colin Allen - 2008 - Oxford University Press.
The Cognitive Informatics Approach Towards Wisdom.Andrew Targowski - 2010 - Dialogue and Universalism 20 (9-10):51-82.
Building Empathic Agents? Comment on “Computational Modelling of Culture and Affect” by Aylett and Paiva.Toyoaki Nishida - 2012 - Emotion Review 4 (3):269-270.