Introduction Connectionist networks have earned recognition in many domains that can be characterised as hard or impossible to explicitly formalise, e.g., driving cars (Pomerleau, 1993), emotion recognition (Cottrell and Metcalfe, 1990) and pronunciation (Sejnowski and Rosenberg, 1987). Connectionists have also claimed that their networks can exhibit behaviours that can be described by a set of formal rules, without actually implementing explicit rule following (McClelland & Rumelhart 1985). The radical implication of this claim is that connectionism does not appear to neatly line up with the classical view of the cognitive architecture, i.e., the computational, the representational and the implementational levels (cf., Marr 1982; Pylyshyn 1984; Newell 1986; Andersson 1983). The intention of this chapter is to investigate a number of different aspects of this claim. We will compare two computationally equivalent systems. The behaviour of both these systems can be described by

Introduction Natural language processing appears on the surface to be a strongly symbolic activity. Words are symbols that stand for objects and concepts in the real world, and they are put together into sentences that obey well-specified grammar rules. It is no surprise that for several decades natural language processing research has been dominated by the symbolic approach. Linguists have focused on describing language systems based on versions of the Universal Grammar. Artificial Intelligence researchers have built large programs where linguistic and world knowledge is expressed in symbolic structures, usually in LISP. Relatively little attention has been paid to various cognitive effects in language processing. Human language users perform differently from their linguistic competence, that is, from their knowledge of how to communicate correctly using language. Some linguistic structures (such as deep embeddings) are harder to deal with than others. People make mistakes wh

In recent years it has been claimed that connectionist methods of representing compositional structures, such as lists and trees, support a new form of symbol processing known as holistic computation. In a holistic computation the constituents of an object are acted upon simultaneously, rather than on a one-by-one basis as is typical in traditional symbolic systems. This thesis presents rstly, a critical examination of the concept of holistic computation, as described in the literature, along with a revised de nition of the concept that aims to clarify the issues involved. In particular it is argued that holistic representations are not necessary for holistic computation and that holistic computation is not restricted to connectionist systems. Secondly, an evaluation of the capacity of a particular connectionist representation, the Sequential RAAM, to generate representations that support holistic symbol processing is presented. It is concluded that the Sequential RAAM is not as eective a vehicle for holistic symbol processing as it initially appeared, but that there may be some scope for improving its performance. Acknowledgements I would like to thank the following people: My supervisor, Peter Hancox, for his support, advice and guidance throughout my PhD. The other members of my thesis group, Russell Beale, Riccardo Poli and Ela Claridge for the advice, questions and suggestions they oered during progress reviews. Additionally I'd like to thank Russell for his comments on this thesis and both Russell and Riccardo for the informal discussions I had with them about my work.

Standard feedforward and recurrent networks cannot support strong systematicity when constituents are presented as local input/output vectors (Phillips, 1998). To explain systematicity connectionists must either: (1) develop alternative models; or (2) justify the assumption of similar (non-local) constituent representations prior to the learning task. I show that the second commonly presumed option cannot account for systematicity, in general. This option, termed first-order connectionism, relies upon established spatial relationships between common-class constituents to account for systematic generalization: Inferences (functions) learned over, e.g., cats extend systematically to dogs by virtue of both being nouns with similar internal representations so that the function learned to make inferences employing one simultaneously has the capacity to make inferences employing the other. But, humans generalize beyond common-class constituents. Cross-category generalization (e.g., inferences that require treating mango as a colour, rather than a fruit) makes having had the necessary common context to learn similar constituent representations highly unlikely. At best, the constituent similarity proposal encodes for one binary relationship between any two constituents, at any one time. It cannot account for inferences, such as transverse patterning that require identifying and applying one of many possible binary constituent relationships that is contingent on a third constituent (i.e., ternary relationship). Connectionists are, therefore, left with the first option which amounts to developing models with the symbol-like capacity to explicitly represent constituent relations independent of constituent contents, such as in tensor-related models. However, rather just simply impl...

It has been claimed that connectionist methods of encoding compositional structures, such as Pollack's RAAM, support a non-classical form of structure sensitive operation known as holistic computation, where symbol structures can be acted upon holistically without the need to decompose them, or to perform a search to locate or access their constituents. In this paper, it is argued that the concept as described in the literature is vague and confused, and a revised definition of holistic computation is proposed which aims to clarify the issues involved. It is also argued that holistic computation neither requires a highly distributed or holistic representation, nor is unique to connectionist methods of representing compositional structure. 2 James A. Hammerton 1 Introduction Developing the ability to represent and process compositional structures, such as lists and trees, within neural networks has been the focus of a considerable amount of recent connectionist research. The lack of t...

. Many believe that the major problem facing traditional artificial intelligence (and the functional theory of mind) is how to connect intelligence to the outside world. Some turned to robotic functionalism and a hybrid response, that attempts to rescue symbolic functionalism by grounding the symbol system with a connectionist hook to the world. Others turned to an alternative approach, embodied cognition, that emerged from an older tradition in biology, ethology, and behavioural modelling. Both approaches are contrasted here before a detailed exploration of embodiment is conducted. In particular we ask whether strong embodiment is possible for robotics, i.e. are robot "minds" similar to animal minds, or is the role of robotics to provide a tool for scientific exploration, a weak embodiment? We define two types of embodiment, Loebian and Uexkullian, that express two different views of the relation between body, mind and behaviour. It is argued that strong embodiment, either Loebian or ...

In this paper we outline hybrid approaches to arti cial neural network-based natural language processing. We start by motivating hybrid symbolic/connectionist processing. Then we suggest various types of symbolic/connectionist integration for language processing: connectionist structure architectures, hybrid transfer architectures, hybrid processing architectures. Furthermore, we focus particularly on loosely coupled, tightly coupled, and fully integrated hybrid processing architectures. We give particular examples of these hybrid processing architectures and argue that the hybrid approach to arti cial neural network-based language processing has a lot of potential to overcome the gap between a neural level and a symbolic conceptual level. ii 1 Motivation for hybrid symbolic/connectionist processing In recent years, the eld of hybrid symbolic/connectionist processing has seen a remarkable

Fodor and Pylyshyn argued that connectionist models could not be used to exhibit and explain a phenomenon that they termed systematicity, i.e., compositional syntax and semantics for mental representations and structure sensitivity of mental processes. This inability, they argued, was particularly serious since it meant that connectionist models could not be used as alternative models to classical symbolic models to explain cognition. In this paper, a connectionist model is used to identify some properties which show that connectionist networks supply means for accomplishing a stronger version of systematicity than Fodor and Pylyshyn opted for. Specifically, it is argued that context-dependent systematicity is achievable within a connectionist framework. The arguments put forward rest on a particular formulation of content and context of connectionist representation, firmly and technically based on connectionist primitives in a learning environment. The perspective is motivated by the fundamental differences between the connectionist and classical architectures, in terms of prerequisites, lower-level functionality and inherent constraints. 2 1

Abstract not found

this paper is to rebut a representative selection of these objections. There are two major reasons for undertaking this project. The first is to provide a partial defense of the DH as an open empirical alternative to the CH. As J.S. Mill put it, "three-fourths of the arguments for every disputed opinion consist in dispelling the appearances which favour some opinion different from it."