Gualtiero Piccinini

A common presupposition in the concepts literature is that concepts constitute a sin- gular natural kind. If, on the contrary, concepts split into more than one kind, this literature needs to be recast in terms of other kinds of mental representation. We offer two new arguments that concepts, in fact, divide into different kinds: (a) concepts split because different kinds of mental representation, processed independently, must be posited to explain different sets of relevant phenomena; (b) concepts split because different kinds of mental representation, processed independently, must be posited to explain responses to different kinds of category. Whether these arguments are sound remains an open empirical question, to be resolved by future empirical and theoretical work.

Computationalism has been the mainstream view of cognition for decades. There are periodic reports of its demise, but they are greatly exaggerated. This essay surveys some recent literature on computationalism. It concludes that computationalism is a family of theories about the mechanisms of cognition. The main relevant evidence for testing it comes from neuroscience, though psychology and AI are relevant too. Computationalism comes in many versions, which continue to guide competing research programs in philosophy of mind as well as psychology and neuroscience. Although our understanding of computationalism has deepened in recent years, much work in this area remains to be done

Abstract: According to the Veridicality Thesis, information requires truth. On this view, smoke carries information about there being a fire only if there is a fire, the proposition that the earth has two moons carries information about the earth having two moons only if the earth has two moons, and so on. We reject this Veridicality Thesis. We argue that the main notions of information used in cognitive science and computer science allow A to have information about the obtaining of p even when p is false.

This paper concerns Alan Turing’s ideas about machines, mathematical methods of proof, and intelligence. By the late 1930s, Kurt Gödel and other logicians, including Turing himself, had shown that no finite set of rules could be used to generate all true mathematical statements. Yet according to Turing, there was no upper bound to the number of mathematical truths provable by intelligent human beings, for they could invent new rules and methods of proof. So, the output of a human mathematician, for Turing, was not a computable sequence (i.e., one that could be generated by a Turing machine). Since computers only contained a finite number of instructions (or programs), one might argue, they could not reproduce human intelligence. Turing called this the “mathematical
objection” to his view that machines can think. Logico-mathematical reasons, stemming from his own work, helped to convince Turing that it should be possible to reproduce human intelligence, and eventually compete with it, by developing the appropriate kind of digital computer. He felt it
should be possible to program a computer so that it could learn or discover new rules, overcoming the limitations imposed by the incompleteness and undecidability results in the same way that human
mathematicians presumably do.

This paper offers an account of what it is for a physical system to be a computing mechanism—a mechanism that performs computations. A computing mechanism is any mechanism whose functional analysis ascribes it the function of generating outputs strings from input strings in accordance with a general rule that applies to all strings. This account is motivated by reasons that are endogenous to the philosophy of computing, but it may also be seen as an application of recent literature on mechanisms. The account can be used to individuate computing mechanisms and the functions they compute and to taxonomize computing mechanisms based on their computing power. This makes it ideal for grounding the comparison and assessment of computational theories of mind and brain.

I address whether neural networks perform computations in the sense of computability theory and computer science. I explicate and defend
the following theses. (1) Many neural networks compute—they perform computations. (2) Some neural networks compute in a classical way.
Ordinary digital computers, which are very large networks of logic gates, belong in this class of neural networks. (3) Other neural networks
compute in a non-classical way. (4) Yet other neural networks do not perform computations. Brains may well fall into this last class.

Gualtiero Piccinini articulates and defends a mechanistic account of concrete, or physical, computation. A physical system is a computing system just in case it is a mechanism one of whose functions is to manipulate vehicles based solely on differences between different portions of the vehicles according to a rule defined over the vehicles. Physical Computation discusses previous accounts of computation and argues that the mechanistic account is better. Many kinds of computation are explicated, such as digital vs. analog, serial vs. parallel, neural network computation, program-controlled computation, and more. Piccinini argues that computation does not entail representation or information processing although information processing entails computation. Pancomputationalism, according to which every physical system is computational, is rejected. A modest version of the physical Church-Turing thesis, according to which any function that is physically computable is computable by Turing machines, is defended.

We sketch a framework for building a unified science of cognition. This unification is achieved by showing how functional analyses of cognitive capacities can be integrated with the multilevel mechanistic explanations of neural systems. The core idea is that functional analyses are sketches of mechanisms , in which some structural aspects of a mechanistic explanation are omitted. Once the missing aspects are filled in, a functional analysis turns into a full-blown mechanistic explanation. By this process, functional analyses are seamlessly integrated with multilevel mechanistic explanations

Since the cognitive revolution, it has become commonplace that cognition involves both computation and information processing. Is this one claim or two? Is computation the same as information processing? The two terms are often used interchangeably, but this usage masks important differences. In this paper, we distinguish information processing from computation and examine some of their mutual relations, shedding light on the role each can play in a theory of cognition. We recommend that theorists of cognition be explicit and careful in choosing notions of computation and information and connecting them together.Keywords: Computation; Information processing; Computationalism; Computational theory of mind; Cognitivism.

The following three theses are inconsistent: (1) (Paradigmatic) connectionist systems perform computations. (2) Performing computations requires executing programs. (3) Connectionist systems do not execute programs. Many authors embrace (2). This leads them to a dilemma: either connectionist systems execute programs or they don't compute. Accordingly, some authors attempt to deny (1), while others attempt to deny (3). But as I will argue, there are compelling reasons to accept both (1) and (3). So, we should replace (2) with a more satisfactory account of computation. Once we do, we can see more clearly what is peculiar to connectionist computation

In the 1950s, Alan Turing proposed his influential test for machine intelligence, which involved a teletyped dialogue between a human player, a machine, and an interrogator. Two readings of Turing's rules for the test have been given. According to the standard reading of Turing's words, the goal of the interrogator was to discover which was the human being and which was the machine, while the goal of the machine was to be indistinguishable from a human being. According to the literal reading, the goal of the machine was to simulate a man imitating a woman, while the interrogator – unaware of the real purpose of the test – was attempting to determine which of the two contestants was the woman and which was the man. The present work offers a study of Turing's rules for the test in the context of his advocated purpose and his other texts. The conclusion is that there are several independent and mutually reinforcing lines of evidence that support the standard reading, while fitting the literal reading in Turing's work faces severe interpretative difficulties. So, the controversy over Turing's rules should be settled in favor of the standard reading.

According to the zombie conceivability argument, phenomenal zombies are conceivable, and hence possible, and hence physicalism is false. Critics of the conceivability argument have responded by denying either that zombies are conceivable or that they are possible. Much of the controversy hinges on how to establish and understand what is conceivable, what is possible, and the link between the two—matters that are at least as obscure and controversial as whether consciousness is physical. Because of this, the debate over physicalism is unlikely to be resolved by thinking about zombies—or at least, zombies as discussed by philosophers to date.



In this paper, I explore an alternative strategy against the zombie conceivability argument. I accept the possibility of zombies and ask whether that possibility is accessible (in the sense of ‘accessible’ used in possible world semantics) to our world. It turns out that the question of whether zombie worlds are accessible to our world is equivalent to the question of whether physicalism is true. By assuming that zombie worlds are accessible to our world, supporters of the zombie conceivability argument beg the question against physicalists. I will then consider what happens if a supporter of the zombie conceivability argument should insist that zombie worlds are accessible to our world. I will argue that the same ingredients used in the zombie conceivability argument—whatever they might be—can be used to construct an argument to the opposite conclusion. If that is correct, we reach a stalemate between physicalism and property dualism: while the possibility of some zombies entails property dualism, the possibility of other creatures entails physicalism. Since these two possibilities are inconsistent, one of them is not genuine. To resolve this stalemate, we need more than thought experiments.

We begin by distinguishing computationalism from a number of other theses that are sometimes conflated with it. We also distinguish between several important kinds of computation: computation in a generic sense, digital computation, and analog computation. Then, we defend a weak version of computationalism—neural processes are computations in the generic sense. After that, we reject on empirical grounds the common assimilation of neural computation to either analog or digital computation, concluding that neural computation is sui generis. Analog computation requires continuous signals; digital computation requires strings of digits. But current neuroscientific evidence indicates that typical neural signals, such as spike trains, are graded like continuous signals but are constituted by discrete functional elements (spikes); thus, typical neural signals are neither continuous signals nor strings of digits. It follows that neural computation is sui generis. Finally, we highlight three important consequences of a proper understanding of neural computation for the theory of cognition. First, understanding neural computation requires a specially designed mathematical theory (or theories) rather than the mathematical theories of analog or digital computation. Second, several popular views about neural computation turn out to be incorrect. Third, computational theories of cognition that rely on non-neural notions of computation ought to be replaced or reinterpreted in terms of neural computation

Some philosophers have conflated functionalism and computationalism. I reconstruct how this came about and uncover two assumptions that made the conflation possible. They are the assumptions that (i) psychological functional analyses are computational descriptions and (ii) everything may be described as performing computations. I argue that, if we want to improve our understanding of both the metaphysics of mental states and the functional relations between them, we should reject these assumptions. # 2004 Elsevier Ltd. All rights reserved

This paper offers an account of what it is for a physical system to be a computing mechanism—a system that performs computations. A computing mechanism is a mechanism whose function is to generate output strings from input strings and (possibly) internal states, in accordance with a general rule that applies to all relevant strings and depends on the input strings and (possibly) internal states for its application. This account is motivated by reasons endogenous to the philosophy of computing, namely, doing justice to the practices of computer scientists and computability theorists. It is also an application of recent literature on mechanisms, because it assimilates computational explanation to mechanistic explanation. The account can be used to individuate computing mechanisms and the functions they compute and to taxonomize computing mechanisms based on their computing power.

Despite its significance in neuroscience and computation, McCulloch and Pitts's celebrated 1943 paper has received little historical and philosophical attention. In 1943 there already existed a lively community of biophysicists doing mathematical work on neural networks. What was novel in McCulloch and Pitts's paper was their use of logic and computation to understand neural, and thus mental, activity. McCulloch and Pitts's contributions included (i) a formalism whose refinement and generalization led to the notion of finite automata (an important formalism in computability theory), (ii) a technique that inspired the notion of logic design (a fundamental part of modern computer design), (iii) the first use of computation to address the mind–body problem, and (iv) the first modern computational theory of mind and brain.

We outline a framework of multilevel neurocognitive mechanisms that incorporates representation and computation. We argue that paradigmatic explanations in cognitive neuroscience fit this framework and thus that cognitive neuroscience constitutes a revolutionary break from traditional cognitive science. Whereas traditional cognitive scientific explanations were supposed to be distinct and autonomous from mechanistic explanations, neurocognitive explanations aim to be mechanistic through and through. Neurocognitive explanations aim to integrate computational and representational functions and structures across multiple levels of organization in order to explain cognition. To a large extent, practicing cognitive neuroscientists have already accepted this shift, but philosophical theory has not fully acknowledged and appreciated its significance. As a result, the explanatory framework underlying cognitive neuroscience has remained largely implicit. We explicate this framework and demonstrate its contrast with previous approaches

Computation and information processing are among the most fundamental notions in cognitive science. They are also among the most imprecisely discussed. Many cognitive scientists take it for granted that cognition involves computation, information processing, or both – although others disagree vehemently. Yet different cognitive scientists use ‘computation’ and ‘information processing’ to mean different things, sometimes without realizing that they do. In addition, computation and information processing are surrounded by several myths; first and foremost, that they are the same thing. In this paper, we address this unsatisfactory state of affairs by presenting a general and theory-neutral account of computation and information processing. We also apply our framework by analyzing the relations between computation and information processing on one hand and classicism and connectionism on the other. We defend the relevance to cognitive science of both computation, in a generic sense that we fully articulate for the first time, and information processing, in three important senses of the term. Our account advances some foundational debates in cognitive science by untangling some of their conceptual knots in a theory-neutral way. By leveling the playing field, we pave the way for the future resolution of the debates’ empirical aspects.

The received view is that computational states are individuated at least in part by their semantic properties. I offer an alternative, according to which computational states are individuated by their functional properties. Functional properties are specified by a mechanistic explanation without appealing to any semantic properties. The primary purpose of this paper is to formulate the alternative view of computational individuation, point out that it supports a robust notion of computational explanation, and defend it on the grounds of how computational states are individuated within computability theory and computer science. A secondary purpose is to show that existing arguments for the semantic view are defective.

According to some philosophers, computational explanation is proprietary
to psychology—it does not belong in neuroscience. But neuroscientists routinely offer computational explanations of cognitive phenomena. In fact, computational explanation was initially imported from computability theory into the science of mind by neuroscientists, who justified this move on neurophysiological grounds. Establishing the legitimacy and importance of computational explanation in neuroscience is one thing; shedding light on it is another. I raise some philosophical questions pertaining to computational explanation and outline some promising answers that are being developed by a number of authors.

Roughly speaking, computationalism says that cognition is computation, or that cognitive phenomena are explained by the agent‘s computations. The cognitive processes and behavior of agents are the explanandum. The computations performed by the agents‘ cognitive systems are the proposed explanans. Since the cognitive systems of biological organisms are their nervous 1 systems (plus or minus a bit), we may say that according to computationalism, the cognitive processes and behavior of organisms are explained by neural computations. Some people might prefer to say that cognitive systems are ―realized‖ by nervous systems, and thus that—according to computationalism—cognitive computations are ―realized‖ by neural processes. In this paper, nothing hinges on the nature of the relation between cognitive systems and nervous systems, or between computations and neural processes. For present purposes, if a neural process realizes a computation, then that neural process is a computation. Thus, I will couch much of my discussion in terms of nervous systems and neural computation.1 Before proceeding, we should dispense with a possible red herring. Contrary to a common assumption, computationalism does not stand in opposition to connectionism. Connectionism, in the most general and common sense of the term, is the claim that cognitive phenomena are explained (at some level and at least in part) by the processes of neural networks. This is a truism, supported by most neuroscientific evidence. Everybody ought to be a connectionist in this general sense. The relevant question is, are neural processes computations? More precisely, are the neural processes to be found in the nervous systems of organisms computations? Computationalists say ―yes‖, anti-computationalists say ―no‖. This paper investigates whether any of the arguments on offer against computationalism have a chance at knocking it off.2 Ever since Warren McCulloch and Walter Pitts (1943) first proposed it, computationalism has been subjected to a wide range of objections..

I argue that metaphysicians of mind have not done justice to the notion of accessibility between possible worlds. Once accessibility is given its due, physicalism must be reformulated and conceivability arguments must be reevaluated. To reach these conclusions, I explore a novel way of assessing the zombie conceivability argument. I accept that zombies are possible and ask whether that possibility is accessible from our world in the sense of ‘accessible’ used in possible world semantics. It turns out that the question whether zombie worlds are accessible from our world is equivalent to the question whether physicalism is true at our world. By assuming that zombie worlds are accessible from our world, proponents of the zombie conceivability argument beg the question against physicalism. In other words, it is a mistake to assume that the metaphysical possibility of zombies entails that physicalism is false at our world. I will then consider what happens if a proponent of the zombie conceivability argument should insist that zombie worlds are accessible from our world. I will argue that the same ingredients used in the zombie conceivability argument—whatever exactly they might be—can be used to construct an argument to the opposite conclusion. At that point, we reach a stalemate between physicalism and property dualism: while the possibility of zombies entails property dualism, the possibility of other creatures entails physicalism. Since these two possibilities are mutually inconsistent, either one of them is not genuine or one of them is inaccessible from the actual world. To resolve this stalemate, we need more than traditional conceivability arguments.

I argue that neural activity, strictly speaking, is not computation. This is because computation, strictly speaking, is the processing of strings of symbols, and neuroscience shows that there are no neural strings of symbols. This has two consequences. On the one hand, the following widely held consequences of computationalism must either be abandoned or supported on grounds independent of computationalism: (i) that in principle we can capture what is functionally relevant to neural processes in terms of some formalism taken from computability theory (such as Turing Machines), (ii) that it is possible to design computer programs that are functionally equivalent to neural processes in the same sense in which it is possible to design computer programs that are functionally equivalent to each other, (iii) that the study of neural (or mental) computation is independent of the study of neural implementation, (iv) that the Church-Turing thesis applies to neural activity in the sense in which it applies to digital computers. On the other hand, we need to gradually reinterpret or replace computational theories in psychology in terms of theoretical constructs that can be realized by known neural processes, such as the spike trains of neuronal ensembles.

Newell was a founder of artificial intelligence and a pioneer in the use of computer simulations in psychology. In collaboration with J. Cliff Shaw and Herbert A. Simon, Newell developed the first list-processing programming language as well as the earliest computer programs for simulating human problem solving. Over a long and prolific career, he contributed to many techniques, such as protocol analysis and heuristic search, that are now part of psychology and computer science. Colleagues remembered Newell for his deep commitment to science, his care for details, and his inexhaustible energy