David Bourget (Western Ontario)
David Chalmers (ANU, NYU)
Rafael De Clercq
Jack Alan Reynolds
Learn more about PhilPapers
Minds and Machines 17 (4):369-389 (2008)
This article is the second step in our research into the Symbol Grounding Problem (SGP). In a previous work, we defined the main condition that must be satisfied by any strategy in order to provide a valid solution to the SGP, namely the zero semantic commitment condition (Z condition). We then showed that all the main strategies proposed so far fail to satisfy the Z condition, although they provide several important lessons to be followed by any new proposal. Here, we develop a new solution of the SGP. It is called praxical in order to stress the key role played by the interactions between the agents and their environment. It is based on a new theory of meaning—Action-based Semantics (AbS)—and on a new kind of artificial agents, called two-machine artificial agents (AM²). Thanks to their architecture, AM2s implement AbS, and this allows them to ground their symbols semantically and to develop some fairly advanced semantic abilities, including the development of semantically grounded communication and the elaboration of representations, while still respecting the Z condition
|Keywords||Action-based semantics Artificial evolution Communication Hebb’s rule Local selection Symbol Grounding Problem Two-machine artificial agents Zero semantic commitment condition|
|Categories||categorize this paper)|
|Through your library||Configure|
Similar books and articles
Stevan Harnad (2011). Lunch Uncertain [Review Of: Floridi, Luciano (2011) The Philosophy of Information (Oxford)]. [REVIEW] Times Literary Supplement 5664 (22-23).
Dairon Rodríguez, Jorge Hermosillo & Bruno Lara (2012). Meaning in Artificial Agents: The Symbol Grounding Problem Revisited. [REVIEW] Minds and Machines 22 (1):25-34.
Karl F. MacDorman (1998). Feature Learning, Multiresolution Analysis, and Symbol Grounding. Behavioral and Brain Sciences 21 (1):32-33.
Stevan Harnad, Symbol Grounding is an Empirical Problem: Neural Nets Are Just a Candidate Component.
Stevan Harnad (1995). Grounding Symbols in Sensorimotor Categories with Neural Networks. Institute of Electrical Engineers Colloquium on "Grounding Representations.
Vincent C. Müller (2009). Symbol Grounding in Computational Systems: A Paradox of Intentions. [REVIEW] Minds and Machines 19 (4):529-541.
Vincenzo Tagliasco, Towards an Artificial User: The “What” Problem for an Architecture Capable of Developing New Goals.
Added to index2009-01-28
Total downloads36 ( #39,541 of 1,008,547 )
Recent downloads (6 months)1 ( #64,735 of 1,008,547 )
How can I increase my downloads?