paper-with-me

Papers

Symbolic Behaviour in Artificial Intelligence

2021-02-05 · Adam Santoro, Andrew Lampinen, Kory Mathewson, Timothy Lillicrap, David Raposo

The ability to use symbols is the pinnacle of human intelligence, but has yet to be fully replicated in machines. Here we argue that the path towards symbolically fluent artificial intelligence (AI) begins with a reinterpretation of what symbols are, how they come to exist, and how a system behaves when it uses them. We begin by offering an interpretation of symbols as entities whose meaning is established by convention. But crucially, something is a symbol only for those who demonstrably and actively participate in this convention. We then outline how this interpretation thematically unifies the behavioural traits humans exhibit when they use symbols. This motivates our proposal that the field place a greater emphasis on symbolic behaviour rather than particular computational mechanisms inspired by more restrictive interpretations of symbols. Finally, we suggest that AI research explore social and cultural engagement as a tool to develop the cognitive machinery necessary for symbolic behaviour to emerge. This approach will allow for AI to interpret something as symbolic on its own rather than simply manipulate things that are only symbols to human onlookers, and thus will ultimately lead to AI with more human-like symbolic fluency.

📄 PDF Abstract BibTeX arXiv:2102.03406

Code (1)

near32/symbolicbehaviourbenchmark

Similar Papers 제목 키워드 기반

Neural-Symbolic Learning and Reasoning: A Survey and Interpretation

2017-11-10 · Tarek R. Besold, Artur d'Avila Garcez, Sebastian Bader, Howard Bowman 외

The study and understanding of human behaviour is relevant to computer science, artificial intelligence, neural computation, cognitive science, philosophy, psychology, and several other areas. Presupposing cognition as b…

Fault DiagnosisPhilosophySurvey

Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking

2023-12-16 · Daniel Harnack, Christoph Lüth, Lukas Gross, Shivesh Kumar 외

Generating physical movement behaviours from their symbolic description is a long-standing challenge in artificial intelligence (AI) and robotics, requiring insights into numerical optimization methods as well as into fo…

reinforcement-learningReinforcement Learning

Formal Explanations for Neuro-Symbolic AI

2024-10-18 · Sushmita Paul, Jinqiang Yu, Jip J. Dekker, Alexey Ignatiev 외

Despite the practical success of Artificial Intelligence (AI), current neural AI algorithms face two significant issues. First, the decisions made by neural architectures are often prone to bias and brittleness. Second, …

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)

Online Learning and Planning in Cognitive Hierarchies

2023-10-18 · Bernhard Hengst, Maurice Pagnucco, David Rajaratnam, Claude Sammut 외

Complex robot behaviour typically requires the integration of multiple robotic and Artificial Intelligence (AI) techniques and components. Integrating such disparate components into a coherent system, while also ensuring…

From Statistical Relational to Neuro-Symbolic Artificial Intelligence

2020-03-18 · Luc De Raedt, Sebastijan Dumančić, Robin Manhaeve, Giuseppe Marra

Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning. This survey identifies several parallels across seven different dimensions between these tw…

Logical ReasoningPositionSurvey