David Chalmers

This paper explores how an evolutionary process can produce systems that learn. A general framework for the evolution of learning is outlined, and is applied to the task of evolving mechanisms suitable for supervised learning in single-layer neural networks. Dynamic properties of a network’s information-processing capacity are encoded genetically, and these properties are subjected to selective pressure based on their success in producing adaptive behavior in diverse environments. As a result of selection and genetic recombination, various successful learning mechanisms evolve, including the well-known delta rule. The effect of environmental diversity on the evolution of learning is investigated, and the role of different kinds of emergent phenomena in genetic and connectionist systems is discussed.

A month ago, I bought an iPhone. The iPhone has already taken over some of the central functions of my brain. It has replaced part of my memory, storing phone numbers and addresses that I once would have taxed my brain with. It harbors my desires: I call up a memo with the names of my favorite dishes when I need to order at a local restaurant. I use it to calculate, when I need to figure out bills and tips. It is a tremendous resource in an argument, with Google ever present to help settle disputes. I make plans with it, using its calendar to help determine what I can and can’t do in the coming months. I even daydream on the iPhone, idly calling up words and images when my concentration slips. Friends joke that I should get the iPhone implanted into my brain. But if Andy Clark is right, all this would do is speed up the processing, and free up my hands. The iPhone is part of my mind already. Clark is a connoisseur of the myriad ways in which the mind relies on the world to get its work done. The first part of this marvelous book explores some of these ways: the extension of our bodies, the extension of our senses, and crucially, the use of language as a tool to extend our thought. The second part of the book defends the thesis that in at least some of these cases, the world is not serving as a mere instrument for the mind. Rather, the relevant parts of the world have become parts of my mind. My iPhone is not my tool, or at least it is not wholly my tool. Parts of it have become parts of me. This is the thesis of the extended mind: when parts of the environment are coupled to the brain in the right way, they become parts of the mind. The thesis has a long history: I am told that there are hints of it in Dewey, Heidegger, and Wittgenstein. But no-one has done as much to give life to the idea as Andy Clark. In a series of important books and articles—Being There, Natural-Born Cyborgs, “Magic words: How language augments human computation”, and many others—he has explored the many ways in which the boundaries between mind and world are far more flexible than one might have thought..

More than a decade ago, philosopher John Searle started a long-running controversy with his paper “Minds, Brains, and Programs” (Searle, 1980a), an attack on the ambitious claims of artificial intelligence (AI). With his now famous _Chinese Room_ argument, Searle claimed to show that despite the best efforts of AI researchers, a computer could never recreate such vital properties of human mentality as intentionality, subjectivity, and understanding. The AI research program is based on the underlying assumption that all important aspects of human cognition may in principle be captured in a computational model. This assumption stems from the belief that beyond a certain level, implementational details are irrelevant to cognition. According to this belief, neurons, and biological wetware in general, have no preferred status as the substrate for a mind. As it happens, the best examples of minds we have at present have arisen from a carbon-based substrate, but this is due to constraints of evolution and possibly historical accidents, rather than to an absolute metaphysical necessity. As a result of this belief, many cognitive scientists have chosen to focus not on the biological substrate of the mind, but instead on the abstract causal structure_ _that the mind embodies (at an appropriate level of abstraction). The view that it is abstract causal structure that is essential to mentality has been an implicit assumption of the AI research program since Turing (1950), but was first articulated explicitly, in various forms, by Putnam (1960), Armstrong (1970) and Lewis (1970), and has become known as _functionalism_. From here, it is a very short step to _computationalism_, the view that computational structure is what is important in capturing the essence of mentality. This step follows from a belief that any abstract causal structure can be captured computationally: a belief made plausible by the Church–Turing Thesis, which articulates the power.

1. I think that by emphasizing theoretical spaces of representations, Andy has put his finger on an issue that is key to connectionism's success, and whose investigation will be a key determinant of the field's further progress. I also think that if we look at representational spaces in the right way, we can see that they are deeply related to classical phenomenon of systematicity in representation. I want to argue that the key to understanding representational spaces, and in particular their ability to capture the deep organization underlying various problems, lies in the idea of what I will call.

Graeme Forbes (2011) raises some problems for two-dimensional semantic theories. The problems concern nested environments: linguistic environments where sentences are nested under both modal and epistemic operators. Closely related problems involving nested environments have been raised by Scott Soames (2005) and Josh Dever (2007). Soames goes so far as to say that nested environments pose the “chief technical problem” for strong two-dimensionalism. We call the problem of handling nested environments within two-dimensional semantics “the nesting problem”. We show that the two-dimensional semantics for attitude ascriptions developed in Chalmers (2011a) has no trouble accommodating certain forms of the nesting problem that involve factive verbs such as “know” or “establish”. A certain form of the nesting problem involving apriority and necessity operators does raise an interesting puzzle, but we show how a generalized version of the nesting problem arises independently of two-dimensional semantics—it arises, in fact, for anyone who accepts the contingent a priori. We, then, provide a two-dimensional treatment of the apriority operator that fits the two-dimensional treatment of attitude verbs and apply it to the generalized nesting problem. We conclude that two-dimensionalism is not seriously threatened by cases involving the nesting of epistemic and modal operators.

It is fairly well-known that certain hard computational problems (that is, 'difficult' problems for a digital processor to solve) can in fact be solved much more easily with an analog machine. This raises questions about the true nature of the distinction between analog and digital computation (if such a distinction exists). I try to analyze the source of the observed difference in terms of (1) expanding parallelism and (2) more generally, infinite-state Turing machines. The issue of discreteness vs continuity will also be touched upon, although it is not so important for analyzing these particular problems.

To clarify the notion of computation and its role in cognitive science, we need an account of implementation, the nexus between abstract computations and physical systems. I provide such an account, based on the idea that a physical system implements a computation if the causal structure of the system mirrors the formal structure of the computation. The account is developed for the class of combinatorial-state automata, but is sufficiently general to cover all other discrete computational formalisms. The implementation relation is non-vacuous, so that criticisms by Searle and others fail. This account of computation can be extended to justify the foundational role of computation in artificial intelligence and cognitive science.

In Section 5 of his interesting article, Goldman suggests that the consideration of imaginary cases can be valuable in the analysis of our psychological concepts. In particular, he argues that we can imagine a system that is isomorphic to us under any functional description, but which lacks qualitative mental states, such as pains and color sensations. Whether or not such a being is empirically possible, it certainly seems to be logically possible, or conceptually coherent. Goldman argues from this possibility to the conclusion that our concepts of qualitative mental states cannot be analyzed entirely in functional terms.

Where does the mind stop and the rest of the world begin? The question invites two standard replies. Some accept the demarcations of skin and skull, and say that what is outside the body is outside the mind. Others are impressed by arguments suggesting that the meaning of our words "just ain't in the head", and hold that this externalism about meaning carries over into an externalism about mind. We propose to pursue a third position. We advocate a very different sort of externalism: an _active externalism_, based on the active role of the environment in driving cognitive processes.

First, I should clarify the notion of "taking consciousness seriously", which serves as a premise in my work. Mulhauser characterizes this as the assumption that no cognitive theory of consciousness will suffice. The latter assumption would indeed beg some crucial questions, but it is not the assumption that I make. I make an assumption about the problem of consciousness, not about any solution. To quote (p. xii): Throughout the book, I have assumed that consciousness exists, and that to redefine the problem as that of explaining how certain cognitive and behavioral functions are performed is unacceptable. This is what I mean by taking consciousness seriously. That is, the premise is simply that there is a phenomenon to be explained, and that the problems of explaining such functions as discrimination, integration, self monitoring, reportability, and so on do not exhaust all the problems in the vicinity. The deepest problem of consciousness, as I understand it, is not the problem of how all these functions are performed, but rather the problem of explaining how and why all this activity supports states of subjective experience.

In article [email protected] writes: Reminds me of a friend of mine who claims that the number 17 is "the most random" number. His proof ran as follows: pick a number. It's not really as good a random number as 17, is it? (Invariable Answer: "Umm, well, no...") This reminds me of a little experiment I did a couple of years ago. I stood on a busy street corner in Oxford, and asked passers by to "name a random number between zero and infinity." I was wondering what this "random" distribution would look like.

Two-dimensional approaches to semantics, broadly understood, recognize two "dimensions" of the meaning or content of linguistic items. On these approaches, expressions and their utterances are associated with two different sorts of semantic values, which play different explanatory roles. Typically, one semantic value is associated with reference and ordinary truth-conditions, while the other is associated with the way that reference and truth-conditions depend on the external world. The second sort of semantic value is often held to play a distinctive role in analyzing matters of cognitive significance and/or context-dependence.

In this paper I use thought-experiments to argue that functional organization fully determines conscious experience. These thought-experiments involve the gradual replacement of neurons by silicon chips, and similar scenarios. I argue that if "absent qualia" or "inverted qualia", are possible, then phenomena I call "fading qualia" and "dancing qualia" will be possible; but I argue that it is very implausible that fading or dancing qualia are possible. The resulting position is a sort of nonreductive functionalism.

In Philosophy Without Intuitions, Herman Cappelen focuses on the metaphilosophical thesis he calls Centrality: contemporary analytic philosophers rely on intuitions as evidence for philosophical theories. Using linguistic and textual analysis, he argues that Centrality is false. He also suggests that because most philosophers accept Centrality, they have mistaken beliefs about their own methods.To put my own views on the table: I do not have a large theoretical stake in the status of intuitions, but unreflectively I find it fairly obvious that many philosophers, including myself, appeal to intuitions. Cappelen’s arguments make a provocative challenge to this unreflective background conception. So it is interesting to work through the arguments to see what they might and might not show.In what follows I aim to articulate a minimal notion of intuition that captures something of the core everyday philosophical usage of the term, and that captures the sense..

To make progress on the problem of consciousness, we have to confront it directly. In this paper, I first isolate the truly hard part of the problem, separating it from more tractable parts and giving an account of why it is so difficult to explain. I critique some recent work that uses reductive methods to address consciousness, and argue that such methods inevitably fail to come to grips with the hardest part of the problem. Once this failure is recognized, the door to further progress is opened. In the second half of the paper, I argue that if we move to a new kind of nonreductive explanation, a naturalistic account of consciousness can be given. I put forward my own candidate for such an account: a nonreductive theory based on principles of structural coherence and organizational invariance, and a double-aspect theory of information.

The project that Dan Lloyd has undertaken is admirable and audacious. He has tried to boil down the substrate of information-processing that underlies conscious experience to some very simple elements, in order to gain a better understanding of the phenomenon. Some people will suspect that by considering a model as simple as a connectionist network, Dan has thrown away everything that is interesting about consciousness. Perhaps there is something to that complaint, but I will take a different tack. It seems to me that if we apply his own reasoning, we can see that Dan has not taken things far _enough_. When we have boiled things down to a system as simple as a connectionist network, it seems faint-hearted to stop there, and perhaps a little arbitrary as well. So I will take things further, and ask what seems to be the really interesting question in the vicinity: what is it like to be a thermostat?

It's very interesting to see neurophysiological evidence brought to bear on the puzzling question of conscious experience. Many have observed that information-processing models of cognition seem to leave consciousness untouched; it is natural to hope that turning to neurophysiology might lead us to the Holy Grail. Still, I think there are reasons to be skeptical. There are good reasons to suppose that neurophysiological investigation contributes to cognitive explanation at best in virtue of constraining the information-processing structure of cognition. Of course this is a very large and significant role for it to play, but it may be over-optimistic to suppose that it can play some further explanatory role, taking us where information-processing theories cannot. If so, then neurophysiological accounts will be no more and no less successful at dealing with consciousness than information-processing accounts are.