Causal theories of mental content (CTs) ground certain aspects of a concept's meaning in the causal relations a concept bears to what it represents. Section 1 explains the problems CTs are meant to solve and introduces terminology commonly used to discuss these problems. Section 2 specifies criteria that any acceptable CT must satisfy. Sections 3, 4, and 5 critically survey various CTs, including those proposed by Fred Dretske, Jerry Fodor, Ruth Garrett Millikan, David Papineau, Dennis Stampe, Dan Ryder, and the (...) author himself. The final section considers general objections to the causal approach. (shrink)

This paper advocates explicitness about the type of entity to be considered as content- bearing in connectionist systems; it makes a positive proposal about how vehicles of content should be individuated; and it deploys that proposal to argue in favour of representation in connectionist systems. The proposal is that the vehicles of content in some connectionist systems are clusters in the state space of a hidden layer. Attributing content to such vehicles is required to vindicate the standard explanation for some (...) classificatory networks’ ability to generalise to novel samples their correct classification of the samples on which they were trained. (shrink)

Despite its centrality in the philosophy of cognitive science, there has been little prior philosophical work engaging with the notion of representation in contemporary NLP practice. This paper attempts to fill that lacuna: drawing on ideas from cognitive science, I introduce a framework for evaluating the representational claims made about components of neural NLP models, proposing three criteria with which to evaluate whether a component of a model represents a property and operationalising these criteria using probing classifiers, a popular analysis (...) technique in NLP (and deep learning more broadly). The project of operationalising a philosophically-informed notion of representation should be of interest to both philosophers of science and NLP practitioners. It affords philosophers a novel testing-ground for claims about the nature of representation, and helps NLPers organise the large literature on probing experiments, suggesting novel avenues for empirical research. (shrink)

The idea that the brain is an information processing system raises some challenging questions about whether information exists independently of brains. Answering these questions is relevant for clarifying the theoretical foundations of the sciences of mind and brain, but also for appropriately interpreting and evaluating the evidence about how brains—and other biological systems—work. This article claims that (1) informational descriptions in the sciences of mind and brain can be genuinely explanatory, despite assuming a mind-dependent notion of information; and (2) that (...) either Popperian objectivity or response-dependence in normal receivers is sufficient for grounding the explanatory role that information often plays in these sciences. Hierarchical predictive processing, which has become a central theoretical framework for neurocognitive research, is used as a case study for supporting these two claims. (shrink)

It is a rare privilege to have such eminent and insightful reviewers. Their kind words about the book are much appreciated – perhaps more than they realise. And I'm grateful to all three for having read the book so constructively. Each has given me several things to think about. In the space available here I will focus on the objections that seem most critical. Robert Rupert argues that I rely on an overly narrow understanding of what the cognitive sciences explain (...) (x1). Elisabeth Camp presses me on what precisely it takes to qualify as a structural representation and raises questions about holism (x2). John Krakauer makes a fundamental objection to positing representations when they seem not to be needed to explain behaviour (x3). Rupert has also provided a useful introduction to the book, so I will jump straight in with my replies. (shrink)

What is the content of a mental state? This question poses the problem of intentionality: to explain how mental states can be about other things, where being about them is understood as representing them. A framework that integrates predictive coding and signaling systems theories of cognitive processing offers a new perspective on intentionality. On this view, at least some mental states are evaluations, which differ in function, operation, and normativity from representations. A complete naturalistic theory of intentionality must account for (...) both types of intentional state. (shrink)

It is a widely accepted thesis in the cognitive sciences and in naturalistic philosophy of mind that the contents of at least some mental representations are innate. A question that has popped up in discussions concerning innate mental representations is this. Are externalist theories of mental content applicable to the content of innate representations? Views on the matter vary and sometimes conflict. To date, there has been no comprehensive assessment of the relationship between content externalism and content innateness. The aim (...) of this paper is to provide such an assessment. I focus on the notions of innateness that are employed in innateness hypotheses within the cognitive sciences and adjacent fields of philosophy, and on causal externalist theories of content. I distinguish between three accounts of what being innate might amount to in innateness hypotheses within the cognitive sciences, and between three types of causal externalism. I explain what the possibility of innate externalistically individuated representations depends upon given all nine combinations. I explain why causal externalism can be true of innate mental representations, given but one of these combinations. (shrink)

Informational theories of semantic content have been recently gaining prominence in the debate on the notion of mental representation. In this paper we examine new-wave informational theories which have a special focus on cognitive science. In particular, we argue that these theories face four important difficulties: they do not fully solve the problem of error, fall prey to the wrong distality attribution problem, have serious difficulties accounting for ambiguous and redundant representations and fail to deliver a metasemantic theory of representation. (...) Furthermore, we argue that these difficulties derive from their exclusive reliance on the notion of information, so we suggest that pure informational accounts should be complemented with functional approaches. (shrink)

The idea that only complex brains can possess genuine representations is an important element in mainstream philosophical thinking. An alternative view, which I label ‘liberal representationalism’, holds that we should accept the existence of many more full-blown representations, from activity in retinal ganglion cells to the neural states produced by innate releasing mechanisms in cognitively unsophisticated organisms. A promising way of supporting liberal representationalism is to show it to be a consequence of our best naturalistic theories of representation. However, several (...) philosophers and scientists have recently argued against this strategy. In the paper I counter these objections in defense of liberal representationalism. (shrink)

Naturalistic theories of representation seek to specify the conditions that must be met for an entity to represent another entity. Although these approaches have been relatively successful in certain areas, such as communication theory or genetics, many doubt that they can be employed to naturalize complex cognitive representations. In this essay I identify some of the difficulties for developing a teleosemantic theory of cognitive representations and provide a strategy for accommodating them: to look into models of signaling in evolutionary game (...) theory. I show how these models can be used to formulate teleosemantics and expand it in new directions. (shrink)

What is the relationship between information and representation? Dating back at least to Dretske (1981), an influential answer has been that information is a rung on a ladder that gets one to representation. Representation is information, or representation is information plus some other ingredient. In this paper, I argue that this approach oversimplifies the relationship between information and representation. If one takes current probabilistic models of cognition seriously, information is connected to representation in a new way. It enters as a (...) property of the represented content as well as a property of the vehicles that carry that content. This offers a new, conceptually and logically distinct way in which information and representation are intertwined in cognition. (shrink)

Causal theories of mental content attempt to explain how thoughts can be about things. They attempt to explain how one can think about, for example, dogs. These theories begin with the idea that there are mental representations and that thoughts are meaningful in virtue of a causal connection between a mental representation and some part of the world that is represented. In other words, the point of departure for these theories is that thoughts of dogs are about dogs because dogs (...) cause the mental representations of dogs. (shrink)

Localizing content in neural networks provides a bridge to understanding the way in which the brain stores and processes information. In this paper, I propose the existence of polytopes in the state space of the hidden layer of feedforward neural networks as vehicles of content. I analyze these geometrical structures from an information-theoretic point of view, invoking mutual information to help define the content stored within them. I establish how this proposal addresses the problem of misclassification and provide a novel (...) solution to the disjunction problem, which hinges on the precise nature of the causal-informational framework for content advocated herein. (shrink)

Neuroscientists have located brain activity that prepares or encodes action plans before agents are aware of intending to act. On the basis of these findings and broader agency research, activity in these regions has been proposed as the neural realizers of practical intention. My aim in this paper is to evaluate the case for taking these neural states to be neural representations of intention. I draw on work in philosophy of action on the role and nature of practical intentions to (...) construct a framework of the functional profile of intentions fit for empirical investigation. With this framework, I turn to the broader empirical neuroscience literature on agency to assess these proposed neural representations of intention. I argue that while these neural states in some respects satisfy the functions of intention in planning agency prospective of action, their fit with the role of intention in action execution is not well supported. I close by offering a sketch of which experimental task features could aid in the search for the neural realizer of intention in action. (shrink)

Representationalists and anti-representationalists disagree about whether a naturalisation of mental content is possible and, hence, whether positing mental representations in cognitive science is justified. Here, I develop a novel way to think about mental representations based on a philosophical description of (cognitive) science inspired by cognitive instrumentalism. On this view, our acceptance of theories positing mental representations and our beliefs in (something like) mental representations do not depend on the naturalisation of content. Thus, I conclude that if we endorse cognitive (...) instrumentalism about mental representations, then we can finally leave the dispute between representationalism and anti-representationalism behind. (shrink)

An influential view in cognitive science is that computation in cognitive systems is semantic, conceptually depending on representation: to compute is to manipulate representations. I argue that accepting the non-semantic teleomechanistic view of computation lays the ground for a promising alternative strategy, in which computation helps to explain and naturalise representation, rather than the other way around. I show that this computation-based approach to representation presents six decisive advantages over the semantic view. I claim that it can improve the two (...) most influential current theories of representation, teleosemantics and structural representation, by providing them with precious tools to tackle some of their main shortcomings. In addition, the computation-based approach opens up interesting new theoretical paths for the project of naturalising representation, in which teleology plays a role in individuating computations, but not representations. (shrink)

This paper deals with the problem of understanding semiosis and meaning in cognitive systems. To this aim we argue for a unified two-factor account according to which both external and internal information are non-independent aspects of meaning, thus contributing as a whole in determining its nature. To overcome the difficulties stemming from this approach we put forward a theoretical scheme based on the definition of a suitable representation space endowed with a set of transformations, and we show how it can (...) be implemented, in the case of a single agent, by a neural network architecture. Numerical experiments conducted on different instances of the latter show that similar representations are developed as a consequence of the fact that these instances are facing a similar semantic task. This allows to model social and environmental influences through a system of interacting agents, each described by a specific implementation of this model architecture. (shrink)