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.