Physical Symbol Systems

By Allen Newell. 1980

Subfields: Cognitive Science & Psychology, Philosophy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Science & Psychology

In Philosophy

Citations in the corpus

The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence (2020, background): “, with a certain kind of reliability as a byproduct. Collectively, these four assumptions about variables, bindings, instances, and operations over variables comprise the core of symbol-manipulation (Newell, 1980; Marcus, 2001). (Symbols themselves are simply ways of encoding things that get used by”
A simple neural network module for relational reasoning (2017, background): “Symbolic approaches to artificial intelligence are inherently relational [16, 5].”
The Symbol Grounding Problem (1990, neutral): “From Newell [28], Pylyshyn [33], Fodor [6] and the classical work by von Neumann, Turing, Grdel, Church, etc. (see ref.”
Rethinking eliminative connectionism. (1998, background): “One popular view, advocated by Fodor (1975) and Newell (1980), assumes that universals are extended through the action of symbol-manipulating machinery.”
Learning by Abstraction: The Neural State Machine (2019, background): “Ideas about compositionality, abstraction and reasoning greatly inspired the classical views of artiﬁcial intelligence [74, 65], but have lately been overshadowed by the astounding success of deep learning over a wide spectrum of real-world tasks [33, 63, 82].”
Visual Semantic Reasoning for Image-Text Matching (2019, background): “Symbolic approaches [32] are the earliest form of reasoning in artificial intelligence.”
Cognitive Architectures for Language Agents (2023, unknown): “2012) to achieve flexible, rational, real-time behaviors (Sun, 2004; Newell, 1980; 1992; Anderson and Lebiere, 2003).”
Mind's Eye: Grounded Language Model Reasoning through Simulation (2022, methodology): “Such an experiment-reasoning paradigm has been used by humans for centuries to ground reasoning on complicated problems (Newell, 1980) and transfer learned knowledge to unfamiliar domains (Novak & Gowin, 1984).”
Generative learning structures and processes for generalized connectionist networks (1993, background): “[2] Section 2 summarizes briefly the two dominant research paradigms in computational approaches to learning -symbol processing (SP) systems (Newell, 1980) and connectionist network (CN) models (Feldman & Ballard, 1982; Rumelhart, Hinton, & Williams, 1986) and points out some potentially…”
Language models show human-like content effects on reasoning (2022, background): “A hallmark of abstract reasoning is the ability to systematically perform algebraic operations over variables that can be bound to any entity (Newell, 1980; Fodor and Pylyshyn, 1988): the statement: ‘X is bigger than Y’ logically implies that ‘Y is smaller than X’, no matter the values of X and Y.”
What exactly is acquired during skill acquisition (2011, methodology): “The theoretical basis for this computational modelling of human behaviour is historically rooted in Newell and Simon’s Physical Symbol System Hypothesis (e.g. Newell and Simon, 1976; Newell, 1980; Simon, 1980).”
RNNs Implicitly Implement Tensor Product Representations (2018, unknown): “Compositional symbolic representations are widely held to be necessary for intelligence (Newell, 1980; Fodor & Pylyshyn, 1988), particularly in the domain of language (Montague, 1974).”
Embodied Cognition: A field guide (2003, background): “While it is true that the original notion of a ‘symbol’—as proposed in the physical symbol systems hypothesis [7,85,86]—was quite broad, given the distinctions suggested above, the decision to restrict the use of ‘representation’ to a smaller sub-set of inner states seems reasonable and motivated, a”
Connectionism and cognitive architecture: a critical analysis. (1988, background): “This is why Newell (1980) speaks of computational systems such as brains and Classical computers as “physical symbols systems”.”