Conceptual Spaces for Cognitive Architectures: A lingua franca for different levels of representation

Abstract

During the last decades, many Cognitive Architectures (CAs) have been realized adopting different assumptions about the organization and the representation of their knowledge level. Some of them (e.g. SOAR (Laird, 2012)) adopt a classical symbolic approach, some (e.g. LEABRA O'Reilly and Munakata (2000)) are based on a purely connectionist model, while others (e.g. CLARION (Sun, 2006)) adopt a hybrid approach combining connectionist and symbolic representational levels. Additionally, some attempts (e.g. biSOAR) trying to extend the representational capacities of CAs by integrating diagrammatical representations and reasoning are also available (Kurup & Chandrasekaran, 2007). In this paper we propose a reflection on the role that Conceptual Spaces, a framework developed by Gärdenfors (2000) more than fifteen years ago, can play in the current development of the Knowledge Level in Cognitive Systems and Architectures. In particular, we claim that Conceptual Spaces offer a lingua franca that allows to unify and generalize many aspects of the symbolic, sub-symbolic and diagrammatic approaches (by overcoming some of their typical problems) and to integrate them on a common ground. In doing so we extend and detail some of the arguments explored by Gärdenfors (1997) for defending the need of a conceptual, intermediate, representation level between the symbolic and the sub-symbolic one. In particular we focus on the advantages offered by Conceptual Spaces (with respect to symbolic and sub-symbolic approaches) in dealing with the problem of compositionality of representations based on typicality traits. Additionally, we argue that Conceptual Spaces could offer a unifying framework for interpreting many kinds of diagrammatic and analogical representations. As a consequence, their adoption could also favor the integration of diagrammatical representation and reasoning in CAs

A framework for computational models of human memory

“…1. Vector-symbolic architectures (Gayler 2003) and conceptual spaces (Lieto, Chella, and Frixione 2017) prove that symbolic systems, such as ACT-R (Anderson and Lebiere 1998), can arise from distributed connectionist networks. As such, the choice of symbolic, vector symbolic, or connectionist is a matter of a model's level of description, rather than a theoretical claim.…”

“…By contrast, what is known as the vector-symbolic (Gayler 2003;Plate 1995) or conceptual spaces (Lieto, Chella, and Frixione 2017) approach to modelling explicitly provides an account at both symbolic and sub-symbolic levels of description. In computational, vector-based models of memory, a to-be-remembered item is represented as a vector.…”

Towards a unifying framework for conceptual represention and reasoning in cognitive systems

“…Such a layer is suited i) to extend the knowledge stored in the Long Term Memory of the individual agents; and ii) to provide a more advanced -shared across the architectures-set of reasoning procedures to query, retrieve and reason on conceptual knowledge coupling standard and common-sense reasoning procedures. Such procedures contribute to fill the gap between the existing cognitive architectures and the cat- 13 For the reasons explaining why the framework of the Conceptual Spaces can be considered in Cognitive Architectures an efficacious, intermediate, representational level connecting symbolic and sub-symbolic representations and what are the advantages offered by such framework with respect to some of the main problems affecting the representational level of CAs we refer to [10,33]. egorization heuristics used by human cognition and not previously available (or only partially available) in those systems [38].…”

“…Most existing approaches try to induce conceptual spaces based on distributional semantics by directly accessing huge amounts of textual documents to extract the multidimensional feature vectors that de- 5 It has been shown that such framework presents some advantages if introduced, in general cognitive architectures, as intermediate representational level between the symbolyc and the subsymbolic one (for more details on this issue we remind to [33]. scribe the conceptual spaces [13].…”

The knowledge level in cognitive architectures: Current limitations and possible developments

“…On the other hand this aspect can be formally handled by recurring to Conceptual Spaces (as shown in [47,51]). …”