Since the emergence of what Fodor and Pylyshyn (1988) call 'new connectionism', there can be little doubt that connectionist research has become a significant topic for discussion in the Philosophy of Cognitive Science and the Philosophy of Mind. In addition to the numerous papers on the topic in philosophical journals, almost every recent book in these areas contain at least a brief reference to, or discussion of, the issues raised by connectionist research (see Sterelny 1990, Searle, 1992, and O Nualláin, (...) 1995, for example). Other texts have focused almost exclusively upon connectionist issues (see Clark, 1993, Bechtel and Abrahamsen, 1991 and Lloyd, 1989, for example). Regrettably the discussions of connectionism found in the philosophical literature suffer from a number of deficiencies. My purpose in this paper is to highlight one particular problem and attempt to take a few steps to remedy the situation. (shrink)

Connectionism is a style of modeling based upon networks of interconnected simple processing devices. This style of modeling goes by a number of other names too. Connectionist models are also sometimes referred to as 'Parallel Distributed Processing' (or PDP for short) models or networks.1 Connectionist systems are also sometimes referred to as 'neural networks' (abbreviated to NNs) or 'artificial neural networks' (abbreviated to ANNs). Although there may be some rhetorical appeal to this neural nomenclature, it is in fact misleading as (...) connectionist networks are commonly significantly dissimilar to neurological systems. For this reason, I will avoid using this terminology, other than in direct quotations. Instead, I will follow the practice I have adopted above and use 'connectionist' as my primary term for systems of this kind. (shrink)

According to the standard (recent) history of connectionism (see for example the accounts offered by Hecht-Nielsen (1990: pp. 14-19) and Dreyfus and Dreyfus (1988), or Papert's (1988: pp. 3-4) somewhat whimsical description), in the early days of Classical Computational Theory of Mind (CCTM) based AI research, there was also another allegedly distinct approach, one based upon network models. The work on network models seems to fall broadly within the scope of the term 'connectionist' (see Aizawa 1992), although the term had (...) yet to be coined at the time. These two approaches were "two daughter sciences" according to Papert (1988: p. 3). The fundamental difference between these two 'daughters', lay (according to Dreyfus and Dreyfus (1988: p. 16)) in what they took to be the paradigm of intelligence. Whereas the early connectionists took learning to be fundamental, the traditional school concentrated upon problem solving. (shrink)

Connectionist research first emerged in the 1940s. The first phase of connectionism attracted a certain amount of media attention, but scant philosophical interest. The phase came to an abrupt halt, due to the efforts of Minsky and Papert (1969), when they argued for the intrinsic limitations of the approach. In the mid-1980s connectionism saw a resurgence. This marked the beginning of the second phase of connectionist research. This phase did attract considerable philosophical attention. It was of philosophical interest, as it (...) offered a way of counteracting the conceptual ties to the philosophical traditions of atomism, rationalism, logic, nativism, rule realism and a concern with the role symbols play in human cognitive functioning, which was prevalent as a consequence of artificial intelligence research. The surge in philosophical interest waned, possibly in part due to the efforts of some traditionalists and the so-called black box problem. Most recently, what may be thought of as a third phase of connectionist research, based on so-called deep learning methods, is beginning to show some signs of again exciting philosophical interest. (shrink)

In 1988, Smolensky proposed that connectionist processing systems should be understood as operating at what he termed the `subsymbolic' level. Subsymbolic systems should be understood by comparing them to symbolic systems, in Smolensky's view. Up until recently, there have been real problems with analyzing and interpreting the operation of connectionist systems which have undergone training. However, recently published work on a network trained on a set of logic problems originally studied by Bechtel and Abrahamsen (1991) seems to offer the potential (...) to provide a detailed, empirically based answer to questions about the nature of subsymbols. In this paper, a network analysis procedure and the results obtained using it are discussed. This provides the basis for an insight into the nature of subsymbols, which is surprising. (shrink)

The notion of a ‘symbol’ plays an important role in the disciplines of Philosophy, Psychology, Computer Science, and Cognitive Science. However, there is comparatively little agreement on how this notion is to be understood, either between disciplines, or even within particular disciplines. This paper does not attempt to defend some putatively ‘correct’ version of the concept of a ‘symbol.’ Rather, some terminological conventions are suggested, some constraints are proposed and a taxonomy of the kinds of issue that give rise to (...) disagreement is articulated. The goal here is to provide something like a ‘geography’ of the various notions of ‘symbol’ that have appeared in the various literatures, so as to highlight the key issues and to permit the focusing of attention upon the important dimensions. In particular, the relationship between ‘tokens’ and ‘symbols’ is addressed. The issue of designation is discussed in some detail. The distinction between simple and complex symbols is clarified and an apparently necessary condition for a system to be potentially symbol, or token bearing, is introduced. (shrink)

This introduction begins by posing the question that this Special Issue addresses and briefly considers historical precedents and why the issue is important. The discussion then moves on to the consideration of important milestones in the history of computing, up until the present time. A brief specification of the essential components of computational systems is then offered. The final section introduces the papers that are included in this volume.

In his target article Page proposes a definition of the term “localist.” In this commentary I argue that his definition does not serve to make a principled distinction, as the inclusion of vague terms make it susceptible to some problematic counterexamples.

Clark & Thornton are too hasty in their dismissal of uninformed learning; nonmonotonic processing units show considerable promise on type-2 tasks. I describe a simulation which succeeds on a “pure” type-2 problem. Another simulation challenges Clark & Thornton 's claims about the serendipitous nature of solutions to type-2 problems.

Berkeley [Minds Machines 10 (2000) 1] described a methodology that showed the subsymbolic nature of an artificial neural network system that had been trained on a logic problem, originally described by Bechtel and Abrahamsen [Connectionism and the mind. Blackwells, Cambridge, MA, 1991]. It was also claimed in the conclusion of this paper that the evidence was suggestive that the network might, in fact, count as a symbolic system. Dawson and Piercey [Minds Machines 11 (2001) 197] took issue with this (...) latter claim. They described some lesioning studies that they argued showed that Berkeley’s (2000) conclusions were premature. In this paper, these lesioning studies are replicated and it is shown that the effects that Dawson and Piercey rely upon for their argument are merely an artifact of a threshold function they chose to employ. When a threshold function much closer to that deployed in the original studies is used, the significant effects disappear. (shrink)

This paper engages the controversy as to whether there is a link between Berkeley’s refutation of abstraction and his refutation of materialism. I argue that there is a strong link. In the opening paragraph I show that materialism being true requires and is required by the possibility of abstraction, and that the obviousness of this fact suggests that the real controversy is whether there is a link between Berkeley’s refutation of materialism and his refutation of the possibility of (...) framing abstract incomplete ideas and abstract general ideas. Although Berkeley can still defeat materialism without relying on his arguments that directly refute the possibility of framing abstract incomplete ideas and abstract general ideas, I contend that there is still a strong link between his refutation of materialism and his refutation of the possibility of framing these ideas. First, I show that the truth of the canonic version of materialism, according to which primary qualities are mindindependent and inhere in material substances, requires the possibility of the mind framing both of these ideas. Second, I show that there is a sense in which the truth of materialism is required by the possibility of either of these ideas. (shrink)

There is widespread belief that connectionist networks are dramatically different from classical or symbolic models. However, connectionists rarely test this belief by interpreting the internal structure of their nets. A new approach to interpreting networks was recently introduced by Berkeley et al. (1995). The current paper examines two implications of applying this method: (1) that the internal structure of a connectionist network can have a very classical appearance, and (2) that this interpretation can provide a cognitive theory that cannot (...) be dismissed as a mere implementation. (shrink)

In an attempt to provide a deeper understanding of the early development of Berkeley, this is a reprinting of the manuscript introduction to Principles of Human Knowledge. The manuscript introduction is shown to express a philosophy different from the doctrine he published.

George Berkeley (1685-1753) is the superstar of Irish Philosophy. He entered Trinity College, Dublin, in 1700 and became a fellow in 1707. In 1724 he resigned his Fellowship to become Dean of Derry, and in 1734 he was made Bishop of Cloyne. He settled in Oxford in 1752 and died the following year. The work of George Berkeley is marked by its diversity and range. His writings take in such topics as mathematics, psychology, politics, health, economics, deism and (...) education, as well as that with which he is most associated - philosophy. Whatever topic he dealt with, his grasp of the subject matter was always impressive and his criticisms of his contemporaries often acute. Among the most noteable of the British Empiricists, he took his starting point from Locke's new 'way of ideas', but he rejected abstract ideas and the possibility of real existence outside perception. It is for this doctrine that he is most known - that there is no such thing as matter, and that things are collections of ideas which can exist only in our minds and only for so long as they are perceived. This philosophy, summed up in his phrase 'to be is to be perceived', he termed 'immaterialism'. A.C. Fraser's collection includes a series of what were previously unpublished notes by Berkeley on all the main topics of his philosophy. This, the 1901 edition, was the first complete edition of his works. (shrink)

This work has been selected by scholars as being culturally important, and is part of the knowledge base of civilization as we know it. This work is in the "public domain in the United States of America, and possibly other nations. Within the United States, you may freely copy and distribute this work, as no entity (individual or corporate) has a copyright on the body of the work. Scholars believe, and we concur, that this work is important enough to be (...) preserved, reproduced, and made generally available to the public. We appreciate your support of the preservation process, and thank you for being an important part of keeping this knowledge alive and relevant. (shrink)

Intercultural Pragmatics studies how language systems are used in social encounters between speakers who have different first languages and cultures, yet communicate in a common language. The field first emerged in the early 21st century, joining two seemingly antagonistic approaches to pragmatics research: the cognitive-philosophical approach, which considers intention as an a priori mental state of the speaker, and the sociocultural-interactional approach, which considers it as a post factum construct created by both speaker and hearer though conversation. Istvan Kecskes, an (...) early proponent of intercultural pragmatics, was among the first to propose merging the two to form the socio-cognitive approach now core to the field. In Intercultural Pragmatics, the first book on the subject, Kecskes establishes the foundations of the field, boldly combining the pragmatic view of cooperation with the cognitive view of egocentrism in order to incorporate emerging features of communication. He argues that people cooperate by generating and formulating intention that is relevant to the given actual situational context. At the same time, however, because of their egocentrism they activate the most salient information to their attention in the construction and comprehension of utterances. Within this approach, interlocutors are considered as social beings searching for meaning with individual minds embedded in a socio-cultural collectivity, and intention is a cooperation-directed practice that is governed by relevance which depends on actual situational experience.Intercultural pragmatics is a rapidly-growing field, and the only subfield of pragmatics to incorporate features of intercultural interaction into mainstream pragmatics. This volume offers both a valuable synthesis of current research and a new way to think about pragmatics. (shrink)

George Berkeley (1685-1753), Bishop of Cloyne, was an Irish philosopher and divine who pursued a number of grand causes, contributing to the fields of economics, mathematics, political theory and theology. He pioneered the theory of 'immaterialism', and his work ranges over many philosophical issues that remain of interest today. This volume offers a complete and accurate edition of Berkeley's extant correspondence, including letters both written by him and to him, supplemented by extensive explanatory and critical notes. Alexander Pope (...) famously said 'To Berkeley every virtue under heaven', and a careful reading of the letters reveals a figure worthy of admiration, sheds new light on his personal and intellectual life and provides insight into the broad historical and philosophical currents of his time. The volume will be an invaluable resource for philosophers, modern historians and those interested in Anglo-Irish culture. (shrink)

Philosophers of mind, both in the conceptual analysis tradition and in the empirical informed school, have been implicitly neglecting the potential conceptual role of the Peripheral Nervous System (PNS) in understanding sensory and perceptual states. Instead, the philosophical as well as the neuroscientific literature has been assuming that it is the Central Nervous System (CNS) alone, and more exactly the brain, that should prima facie be taken as conceptually and empirically crucial for a philosophical analysis of such states This is (...) the first monograph that focuses on the PNS and its constitutive role in sensory states, including pain, mechanoception, proprioception, tactile perception, and so forth. -/- The author argues that the brain-centeredness of current philosophy of mind is a prejudice, and proposes a series of original ways in which classic puzzles in the philosophy of mind can be solved once the hypothesis that PNS is a constitutive element of mental states is taken seriously. The author calls this “the Peripheral Mind Hypothesis”, and employs it in a vast range of issues, such as functionalism, physicalism, mental content, embodiment, as well as some issues in neuroethics. -/- Making equal use of conceptual analysis, empirical data from neuroscience, first-person phenomenological data, and philosophical speculation, this work offers a fresh look at, and novel solutions to many philosophical problems. (shrink)

Starting from the theological fragment of Protagoras , the paper explores the possible connections between sceptical views and theology in antiquity. I argue that some standard topics in late antique theological discourse, such as the method of negative theology, the philosophical problem of omnipotence, and the compatibility of human autonomy with divine omniscience stem from sceptical arguments, more particularly from those of Carneades. These sections discuss in detail evidence in passages of Sextus Empiricus, Cicero and of the pseudo-Aristotelian treatise De (...) Melisso, Xenophane, Gorgia. Finally, I point out how the late antique theories of intermediaries meant to explain the problem of Evil could have profited from the application of the sorites argument to theology by Carneades. (shrink)

An important question in language evolution is whether segmentation as a linguistic process is able to yield compositionality. Segmentation is hypothesized to be a process to bridge the gap between holistic and compositional lexicons. However, to date no thorough analytical method has been provided to test the feasibility of segmentation. In this paper, an analytical model is presented that can predict the probability of encountering various kinds of overlaps by observing utterance pairs, and the probability of finding confirmation in the (...) language for newly extracted segments. Language users start by using a previously evolved holistic lexicon to communicate about simple environments. They segment these holistic utterances to smaller pieces, which can be used as elements of a compositional lexicon. The model reveals that the feasibility of segmentation depends on the definition of counterexamples, i.e. those associations (pairs), which either cause ambiguous extraction of segments, or do not allow segmentation at all. On one hand if inexact overlaps are considered to be contradictory (i.e. causing confusion) to a perfect exact overlap, then the probability is so minuscule that it renders the role of segmentation marginal during language evolution. On the other hand, if such inexact counterexamples are able to be segmented unambiguously due to extra cognitive capacities, segmentation may have a much higher feasibility. Keywords: segmentation; fractionation; analysis; holistic; protolanguage; compositionality. (shrink)

Qu'on ne doit pas observer une totale obeissance passive vis-a-vis de n'importe quel pouvoir civil, mais que la soumission au gouvernement doit etre mesuree et limitee par le bien commun de la societe; que donc les sujets peuvent legitimement resister a l'autorite supreme dans le cas precis ou le bien commun parait clairement l'exiger; que dis-je! qu'il est du devoir des sujets de resister dans la mesure ou ils se trouvent tous dans la necessaire obligation de faire fleurir l'interet commun: (...) puisque ces idees et d'autres de la meme farine, que je ne puis m'empecher de juger pernicieuses pour le genre humain et contraires a la droite raison, ont ete cultivees avec assiduites ces dernieres annees par de talentueux hommes de science, il a paru necessaire d'armer contre elles les jeunes gens de notre Universite et de veiller a ce qu'ils fassent leur entree dans le monde fourbis de bons principes. (shrink)

Berkeley's Principles: Expanded and Explained includes the entire classical text of the Treatise Concerning the Principles of Human Knowledge in bold font, a running commentary blended seamlessly into the text in regular font and analytic summaries of each section. The commentary is like a professor on hand to guide the reader through every line of the daunting prose and every move in the intricate argumentation. The unique design helps students learn how to read and engage with one of modern (...) philosophy's most important and exciting classics. (shrink)

If a tree falls in the forest and no one is present to hear it, does it make a sound? It does not, according to George Berkeley. Originally published in 1710, this landmark of Western philosophy introduced a revolutionary concept: immaterialism, which asserts that to be is to perceive or be perceived. The treatise opens with an assault on Locke's theory of abstract ideas and proceeds with arguments that sensible qualities exist only when perceived as ideas. Physical objects, he (...) claims, are no more than collections of qualities, and these sensible objects, too, are merely ideas. Berkeley relates his position to the achievements of eighteenth-century science, and proclaims the compatibility of immaterialism with traditional religion. (shrink)

Historical and actual analyse about the essential relation between the COMPLOT and the Secret !