Many of the computing systems programmed using Machine Learning are opaque: it is difficult to know why they do what they do or how they work. Explainable Artificial Intelligence aims to develop analytic techniques that render opaque computing systems transparent, but lacks a normative framework with which to evaluate these techniques’ explanatory successes. The aim of the present discussion is to develop such a framework, paying particular attention to different stakeholders’ distinct explanatory requirements. Building on an analysis of “opacity” from (...) philosophy of science, this framework is modeled after accounts of explanation in cognitive science. The framework distinguishes between the explanation-seeking questions that are likely to be asked by different stakeholders, and specifies the general ways in which these questions should be answered so as to allow these stakeholders to perform their roles in the Machine Learning ecosystem. By applying the normative framework to recently developed techniques such as input heatmapping, feature-detector visualization, and diagnostic classification, it is possible to determine whether and to what extent techniques from Explainable Artificial Intelligence can be used to render opaque computing systems transparent and, thus, whether they can be used to solve the Black Box Problem. (shrink)

Figure 1: A pr ototyp ical exa mple of a three-layer feed forward network, used by Plunkett and M archm an (1 991 ) to simulate learning the past-tense of En glish verbs. The inpu t units encode representations of the three phonemes of the present tense of the artificial words used in this simulation. Th e netwo rk is trained to produce a representation of the phonemes employed in the past tense form and the suffix (/d/, /ed/, or /t/) (...) used on regular verbs. To run the network, each input unit is assigned an activation value o f 0 or 1 , dep ending on whethe r the featu re is present or not. Eac h input unit is conne cted to each of the 30 hidden units by a we ighted conn ection and p rovid es an inp ut to each hidden unit equal to the product of the input unit's activation and the weight. Each hidd en unit's activation is then determined by summing ov er the va lues co ming fro m each inp ut unit to deter mine a netinput, and then applying a non-linear function (e.g., the logistic function 1/(1+e^netinput). Th is whole proced ure is. (shrink)

This introduction to a special issue of Topoi introduces and summarises the relationship between three main varieties of 'enactivist' theorising about the mind: 'autopoietic', 'sensorimotor', and 'radical' enactivism. It includes a brief discussion of the philosophical and cognitive scientific precursors to enactivist theories, and the relationship of enactivism to other trends in embodied cognitive science and philosophy of mind.

The social brain hypothesis implies that humans and other primates evolved “modules“ for representing social knowledge. Alternatively, no such cognitive specializations are needed because social knowledge is already present in the world — we can simply monitor the dynamics of social interactions. Given the latter idea, what mechanism could account for coalition formation? We propose that statistical learning can provide a mechanism for fast and implicit learning of social signals. Using human participants, we compared learning of social signals with arbitrary (...) signals. We found that learning of social signals was no better than learning of arbitrary signals. While coupling faces and voices led to parallel learning, the same was true for arbitrary shapes and sounds. However, coupling versus uncoupling social signals with arbitrary signals revealed that faces and voices are treated with perceptual priority. Overall, our data suggest that statistical learning is a viable domain-general mechanism for learning social group structure. Keywords: social brain; embodied cognition; distributed cognition; situated cognition; multisensory; audiovisual speech; crossmodal; multimodal. (shrink)

The historical debate on representation in cognitive science and neuroscience construes representations as theoretical posits and discusses the degree to which we have reason to posit them. We reject the premise of that debate. We argue that experimental neuroscientists routinely observe and manipulate neural representations in their laboratory. Therefore, neural representations are as real as neurons, action potentials, or any other well-established entities in our ontology.

This paper attempts to clarify and critically examine Fodor's language of thought (LOT) hypothesis, focusing on his contention that the systematicity of language use provides a solid ground for the LOT hypothesis. (edited).

On the extended mind hypothesis (EM), many of our cognitive states and processes are hybrids, unevenly distributed across biological and nonbiological realms. In certain circumstances, things - artifacts, media, or technologies - can have a cognitive life, with histories often as idiosyncratic as those of the embodied brains with which they couple. The realm of the mental can spread across the physical, social, and cultural environments as well as bodies and brains. My independent aims in this chapter are: first, to (...) describe two compatible but distinct movements or "waves" within the EM literature, arguing for the priority of the second wave (and gesturing briefly toward a third); and, second, to defend and illustrate the interdisciplinary implications of EM as best understood, specifically for historical disciplines, by sketching two case studies. (shrink)

Multiple explanatory frameworks may be required to provide an adequate account of human cognition. This paper embeds the classical account within a neural network framework, exploring the encoding of syntacticallystructured objects over the synchronicdiachronic characteristics of networks. Synchronic structure is defined in terms of temporal binding and the superposition of states. To accommodate asymmetric relations, synchronic structure is subject to the type uniqueness constraint. The nature of synchronic structure is shown to underlie Xbar theory that characterizes the phrasal structure of (...) human languages. The derivation differentiates core Xbar properties from languagespecific properties. (shrink)

Despite a wealth of data we still have no clear idea what color experiences represent. In fact, color experiences vary with so many factors that it has been claimed that they do not represent anything at all. The primary challenge for any representational account of color experience is to accommodate the various psychophysical results that demonstrate that color appearance depends not only on the spectral nature of the target but also on the spectral, spatial and figural nature of the surround. (...) A number of theorists have proposed that this dependence is an aspect of the visual system's constancy mechanism. However this does not in and of itself tell us what, if anything, is represented in color experience. Ultimately the answer to this question will be informed by one's theory of representational content. I will argue that adopting a molecular scheme of representation enables the development of an account of the represented object of color experience that can do justice to the psychophysical data. (shrink)

How can abductive reasoning be physical, feasible, and reliable? This is Fodor’s riddle of abduction, and its apparent intractability is the cause of Fodor’s recent pessimism regarding the prospects for cognitive science. I argue that this riddle can be solved if we augment the computational theory of mind to allow for non-computational mental processes, such as those posited by classical associationists and contemporary connectionists. The resulting hybrid theory appeals to computational mechanisms to explain the semantic coherence of inference and associative (...) mechanisms to explain the efficient retrieval of relevant information from memory. The interaction of these mechanisms explains how abduction can be physical, feasible, and reliable. (shrink)

Fodor has argued that observation is theory neutral, since the perceptual systems are modular, that is, they are domain‐specific, encapsulated, mandatory, fast, hard‐wired in the organism, and have a fixed neural architecture. Churchland attacks the theoretical neutrality of observation on the grounds that (a) the abundant top‐down pathways in the brain suggest the cognitive penetration of perception and (b) perceptual learning can change in the wiring of the perceptual systems. In this paper I introduce a distinction between sensation, perception, and (...) observation and I argue that although Churchland is right that observation involves top‐down processes, there is also a substantial amount of information in perception which is theory‐neutral. I argue that perceptual learning does not threaten the cognitive impenetrability of perception, and that the neuropsychological research does not provide evidence in favor of the top‐down character of perception. Finally, I discuss the possibility of an off‐line cognitive penetrability of perception. (shrink)

Fodor's theory makes thinking prior to doing. It allows for an inactive agent or pure reflector, and for agents whose actions in various ways seem to float free of their own conceptual repertoires. We show that naturally evolved creatures are not like that. In the real world, thinking is always and everywhere about doing. The point of having a brain is to guide the actions of embodied beings in a complex material world. Some of those actions are, to be sure, (...) more recondite than others. But in every case the contents of thoughts still look to depend, in some non‐unique but vitally important way, on the kinds of doings they support. (shrink)

When cognitive scientists apply computational theory to the problem of phenomenal consciousness, as many of them have been doing recently, there are two fundamentally distinct approaches available. Either consciousness is to be explained in terms of the nature of the representational vehicles the brain deploys; or it is to be explained in terms of the computational processes defined over these vehicles. We call versions of these two approaches _vehicle_ and _process_ theories of consciousness, respectively. However, while there may be space (...) for vehicle theories of consciousness in cognitive science, they are relatively rare. This is because of the influence exerted, on the one hand, by a large body of research which purports to show that the explicit representation of information in the brain and conscious experience are _dissociable_, and on the other, by the _classical_ computational theory of mind – the theory that takes human cognition to be a species of symbol manipulation. But two recent developments in cognitive science combine to suggest that a reappraisal of this situation is in order. First, a number of theorists have recently been highly critical of the experimental methodologies employed in the dissociation studies – so critical, in fact, it’s no longer reasonable to assume that the dissociability of conscious experience and explicit representation has been adequately demonstrated. Second, classicism, as a theory of human cognition, is no longer as dominant in cognitive science as it once was. It now has a lively competitor in the form of _connectionism; _and connectionism, unlike classicism, does have the computational resources to support a robust vehicle theory of consciousness. In this paper we develop and defend this connectionist vehicle theory of consciousness. It takes the form of the following simple empirical hypothesis: _phenomenal experience consists in the explicit_ _representation of information in neurally realized PDP networks_.. (shrink)

One of the principal tasks Dennett sets himself in Consciousness Explained is to demolish the Cartesian theater model of phenomenal consciousness, which in its contemporary garb takes the form of Cartesian materialism: the idea that conscious experience is a process of presentation realized in the physical materials of the brain. The now standard response to Dennett is that, in focusing on Cartesian materialism, he attacks an impossibly naive account of consciousness held by no one currently working in cognitive science or (...) the philosophy of mind. Our response is quite different. We believe that, once properly formulated, Cartesian materialism is no straw man. Rather, it is an attractive hypothesis about the relationship between the computational architecture of the brain and phenomenal consciousness, and hence one that is worthy of further exploration. Consequently, our primary aim in this paper is to defend Cartesian materialism from Dennett’s assault. We do this by showing that Dennett’s argument against this position is founded on an implicit assumption (about the relationship between phenomenal experience and information coding in the brain), which while valid in the context of classical cognitive science, is not forced on connectionism. (shrink)

When it comes to applying computational theory to the problem of phenomenal consciousness, cognitive scientists appear to face a dilemma. The only strategy that seems to be available is one that explains consciousness in terms of special kinds of computational processes. But such theories, while they dominate the field, have counter-intuitive consequences; in particular, they force one to accept that phenomenal experience is composed of information processing effects. For cognitive scientists, therefore, it seems to come down to a choice between (...) a counter-intuitive theory or no theory at all. We offer a way out of this dilemma. We argue that the computational theory of mind doesn't force cognitive scientists to explain consciousness in terms of computational processes, as there is an alternative strategy available: one that focuses on the representational vehicles that encode information in the brain. This alternative approach to consciousness allows us to do justice to the standard intuitions about phenomenal experience, yet remain within the confines of cognitive science. (shrink)

Dead reckoning is a feature of the navigation behaviour shown by several creatures, including the desert ant. Recent work by C. Randy Gallistel shows that some connectionist models of dead reckoning face important challenges. These challenges are thought to arise from essential features of the connectionist approach, and have therefore been taken to show that connectionist models are unable to explain even the most primitive of psychological phenomena. I show that Gallistel’s challenges are successfully met by one recent connectionist model, (...) proposed by Ulysses Bernardet, Sergi Bermúdez i Badia, and Paul F.M.J. Verschure. The success of this model suggests that there are ways to implement dead reckoning with neural circuits that fall within the bounds of what many people regard as neurobiologically plausible, and so that the wholesale dismissal of the connectionist modelling project remains premature. (shrink)