Symbol Grounding Problems and Sensor Design
نویسنده
چکیده
By Newell and Simon’s [NS81] definition, the semantics and pragmatics of a Physical Symbol System (PSS) are measured ecologically. To fund intelligence, then, some symbols within a PSS must refer to environmental features. To ground these symbols, a PSS must use sensors that gather environmental information for translation into symbolic form. When attempting to divine a PSS’s purpose, the engineer must examine the PSS within its environment. She must, therefore, adopt the role of field linguist: matching posited symbol to environmental referent requires construction of an ontology and translation manual. However, exotic cases of ontology, purpose, sensor and environment, present a task of interpretation as radical as that faced when searching for intelligent extraterrestrial signals: the engineer lacks foreknowledge of the physical and temporal granularity at which to search and of the purpose served by the message. Theoretically, then, she may be limited to recognising PSSs whose ontologies, purposes, sensors and environments are akin to her own, and she may be in danger of imposing the very semantics she seeks to recognise.
منابع مشابه
Symbol Grounding - the Emperor ' s New Theory of Meaning ? Morten
What is the relationship between cognitive theories of symbol grounding and philosophical theories of meaning? In this paper we argue that, although often considered to be fundamentally distinct, the two are actually very similar. Both set out to explain how non-referring atomic tokens or states of a system can acquire status as semantic primitives within that system. In view of this close rela...
متن کاملEquivalence of the Symbol Grounding and Quantum System Identification Problems
The symbol grounding problem is the problem of specifying a semantics for the representations employed by a physical symbol system in a way that is neither circular nor regressive. The quantum system identification problem is the problem of relating observational outcomes to specific collections of physical degrees of freedom, i.e., to specific Hilbert spaces. It is shown that with reasonable p...
متن کاملMachine Symbol Grounding and Optimization
Autonomous systems gather high-dimensional sensorimotor data with their multimodal sensors. Symbol grounding is about whether these systems can, based on this data, construct symbols that serve as a vehicle for higher symbol-oriented cognitive processes. Machine learning and data mining techniques are geared towards finding structures and input-output relations in this data by providing appropr...
متن کاملOn Machine Symbol Grounding and Optimization
From the point of view of an autonomous agent the world consists of high-dimensional dynamic sensorimotor data. Interface algorithms translate this data into symbols that are easier to handle for cognitive processes. Symbol grounding is about whether these systems can, based on this data, construct symbols that serve as a vehicle for higher symbol-oriented cognitive processes. Machine learning ...
متن کاملThe Acquisition of New Categories through Grounded Symbols: An Extended Connectionist Model
Solutions to the symbol grounding problem, in psychologically plausible cognitive models, have been based on hybrid connectionist/symbolic architectures, on robotic approaches and on connectionist only systems. This paper presents new simulations on the use of neural network architectures for the grounding of symbols on categories. In particular, the connectivity patterns between layers of the ...
متن کامل