The paper offers a solution to the generality problem for a reliabilist epistemology, by developing an “algorithm and parameters” scheme for type-individuating cognitive processes. Algorithms are detailed procedures for mapping inputs to outputs. Parameters are psychological variables that systematically affect processing. The relevant process type for a given token is given by the complete algorithmic characterization of the token, along with the values of all the causally relevant parameters. The typing that results is far removed from the typings of folk (...) psychology, and from much of the epistemology literature. But it is principled and empirically grounded, and shows good prospects for yielding the desired epistemological verdicts. The paper articulates and elaborates the theory, drawing out some of its consequences. Toward the end, the fleshed-out theory is applied to two important case studies: hallucination and cognitive penetration of perception. (shrink)

Terrence Deacon's views about the origin of language are based on a particular notion of a symbol. While the notion is derived from Peirce's semiotics, it diverges from that source and needs to be investigated on its own terms in order to evaluate the idea that the human species has crossed the symbolic threshold. Deacon's view is defended from the view that symbols in the animal world are widespread and from the extreme connectionist view that they are not even to (...) be found in humans. Deacon's treatment of symbols involves a form of holism, as a symbol needs to be part of a system of symbols. He also appears to take a realist view of symbols. That combination of holism and realism makes the threshold a sharp threshold, which makes it hard to explain how the threshold was crossed. This difficulty is overcome if we take a mild realist position towards symbols, in the style of Dennett. Mild realism allows intermediate stages in the crossing but does not undermine Deacon's claim that the threshold is difficult to cross or the claim that it needs to be crossed quickly. (shrink)

The philosophy of information (PI) is a new area of research with its own field of investigation and methodology. This article, based on the Herbert A. Simon Lecture of Computing and Philosophy I gave at Carnegie Mellon University in 2001, analyses the eighteen principal open problems in PI. Section 1 introduces the analysis by outlining Herbert Simon's approach to PI. Section 2 discusses some methodological considerations about what counts as a good philosophical problem. The discussion centers on Hilbert's famous analysis (...) of the central problems in mathematics. The rest of the article is devoted to the eighteen problems. These are organized into five sections: problems in the analysis of the concept of information, in semantics, in the study of intelligence, in the relation between information and nature, and in the investigation of values. (shrink)

By pointing to deep philosophical confusions endemic to cognitive science, Wittgenstein might seem an enemy of computational approaches. We agree that while Wittgenstein would reject the classicist’s symbols and rules approach, his observations align well with connectionist or neural network approaches. While many connectionisms that dominated the later twentieth century could fall prey to criticisms of biological, pedagogical, and linguistic implausibility, current connectionist approaches can resolve those problems in a Wittgenstein-friendly manner. We present the basics of a Vector Symbolic Architecture (...) formalism, inspired by Smolensky, and indicate how high-dimensional vectors can operate in a context-sensitive and object-independent manner in biologically plausible time scales, reflecting Wittgenstein’s notions of language-games and family resemblance; we show how “soft” symbols for such a formalism can be formed with plausible learning cycles using Sparse Distributed Memory, resolving disputes surrounding Wittgenstein’s private language argument; and show how connectionist networks can extrapolate meaningful patterns to solve problems, providing “ways to go on” without explicit rules, which indicates linguistic plausibility. Connectionism thus provides a systematicity and productivity that is more than a mere implementation of a classical approach, and provides Wittgenstein-friendly and Wittgenstein-illuminating models of mind and language for cognitive science. (shrink)

Connectionism and phenomenology can mutually inform and mutually constrain each other. In this manifesto I outline an approach to consciousness based on distinctions developed by connectionists. Two core identities are central to a connectionist theory of consciouness: conscious states of mind are identical to occurrent activation patterns of processing units; and the variable dispositional strengths on connections between units store latent and unconscious information. Within this broad framework, a connectionist model of consciousness succeeds according to the degree of correspondence between (...) the content of human consciousness (the world as it is experienced) and the interpreted content of the network. Constitutive self-awareness and reflective self-awareness can be captured in a model through its ability to respond to self-reflexive information, identify self-referential categories, and process information in the absence of simultaneous input. The qualitative feel of sensation appears in a model as states of activation that are not fully discriminated by later processing. Connectionism also uniquely explains several specific features of experience. The most important of these is the superposition of information in consciousness — our ability to perceive more than meets the eye, and to apprehend complex categorical and temporal information in a single highly-cognized glance. This superposition in experience matches a superposition of representational content in distributed representations. (shrink)

This article presents counter evidence against Smolensky's theory that human intuitive/nonconscious congnitive processes can only be accurately explained in terms of subsymbolic computations carried out in artificial neural networks. We presentsymboliclearning models of two well‐studied, complicated cognitive tasks involving nonconscious acquisition of information: learning production rules and artificial finite state grammars. Our results demonstrate that intuitive learning does not imply subsymbolic computation, and that the already well‐established, perceived correlation between “conscious” and “symbolic” on the one hand, and between “nonconscious” and (...) “subsymbolic” on the other, does not exist. (shrink)

Segregated neural circuits that effect particular domain-specific behaviors can be differentiated from neuroanatomical structures implicated in many different aspects of behavior. The basal ganglionic components of circuits regulating nonlinguistic motor behavior, speech, and syntax all function in a similar manner. Hence, it is unlikely that special properties and evolutionary mechanisms are associated with the neural bases of human language.

On the basis of impossibility results on probability, belief revision, and conditionals, it is argued that conditional beliefs differ from beliefs in conditionals qua mental states. Once this is established, it will be pointed out in what sense conditional beliefs are still conditional, even though they may lack conditional contents, and why it is permissible to still regard them as beliefs, although they are not beliefs in conditionals. Along the way, the main logical, dispositional, representational, and normative properties of conditional (...) beliefs are studied, and it is explained how the failure of not distinguishing conditional beliefs from beliefs in conditionals can lead philosophical and empirical theories astray. (shrink)

The concepts and powerful mathematical tools of Dynamical Systems Theory (DST) yield illuminating methods of studying cognitive processes, and are even claimed by some to enable us to bridge the notorious explanatory gap separating mind and matter. This article includes an analysis of some of the conceptual and empirical progress Dynamical Systems Theory is claimed to accomodate. While sympathetic to the dynamicist program in principle, this article will attempt to formulate a series of problems the proponents of the approach in (...) question will need to face if they wish to prolong their optimism. The main points to be addressed involve the reductive tendencies inherent in Dynamical Systems Theory, its somewhat muddled position relative to connectionism, the metaphorical nature DST-C exhibits which hinders its explanatory potential, and DST-C's problematic account of causality. Brief discussions of the mathematical and philosophical backgrounds of DST, seminal experimental work and possible adaptations of the theory or alternative suggestions (dynamicist connectionism, neurophenomenology, R&D theory) are included. (shrink)

A cognitive architecture aimed at cumulative learning must provide the necessary information and control structures to allow agents to learn incrementally and autonomously from their experience. This involves managing an agent's goals as well as continuously relating sensory information to these in its perception-cognition information processing stack. The more varied the environment of a learning agent is, the more general and flexible must be these mechanisms to handle a wider variety of relevant patterns, tasks, and goal structures. While many researchers (...) agree that information at different levels of abstraction likely differs in its makeup and structure and processing mechanisms, agreement on the particulars of such differences is not generally shared in the research community. A dual processing architecture has been proposed as a model of cognitive processing, and they are often considered as responsible for low- and high-level information, respectively. We posit that cognition is not binary in this way and that knowledge at any level of abstraction involves what we refer to as neurosymbolic information, meaning that data at both high and low levels must contain both symbolic and subsymbolic information. Further, we argue that the main differentiating factor between the processing of high and low levels of data abstraction can be largely attributed to the nature of the involved attention mechanisms. We describe the key arguments behind this view and review relevant evidence from the literature. (shrink)

Shastri & Ajjanagadde argue convincingly that both structured connectionist networks and parallel dynamic inferencing are necessary for reflexive reasoning - a kind of inferencing and reasoning that occurs rapidly, spontaneously, and without conscious effort, and which seems necessary for everyday tasks such as natural language understanding. As S&A describe, reflexive reasoning requires a solution to thedynamic binding problem, that is, how to encode systematic and abstract knowledge and instantiate it in specific situations to draw appropriate inferences. Although symbolic artificial intelligence (...) systems trivially solve the dynamic binding problem using computers' registers and pointers, it has remained a difficult problem for connectionist systems. S&A's temporal synchrony solution to the dynamic binding problem using synchronous firing of argument units and the entities that are bound to them illustrates one way in which connectionist networks can do thisusing a constrained but important class of long-term knowledge rules. Their structured connectionist solution allows dynamic inferencing to proceed in parallel and therefore has a number of advantages for reflexive reasoning over most other connectionist and symbolic systems. (shrink)

Hebbian cell-assembly theory and attractor networks are good starting points for modeling cortical processing. Detailed cell models can be useful in understanding the dynamics of attractor networks. Cell assemblies are likely to be distributed, with the cortical column as the local processing unit. Synaptic memory may be dominant in all but the first couple of seconds.

As AI systems become increasingly complex it may become unclear, even to the designer of a system, why exactly a system does what it does. This leads to a lack of trust in AI systems. To solve this, the field of explainable AI has been working on ways to produce explanations of these systems’ behaviors. Many methods in explainable AI, such as LIME, offer only a statistical argument for the validity of their explanations. However, some methods instead study the internal (...) structure of the system and try to find components which can be assigned an interpretation. I believe that these methods provide more valuable explanations than those statistical in nature. I will try to identify which explanations can be considered internal to the system using the Chomskyan notion of tacit knowledge. I argue that each explanation expresses a rule, and through the localization of this rule in the system internals, we can take a system to have tacit knowledge of the rule. I conclude that the only methods which are able to sufficiently establish this tacit knowledge are those along the lines of Olah : 4901–4911, 2017), and therefore they provide explanations with unique strengths. (shrink)

The Visual World Paradigm (VWP) presents listeners with a challenging problem: They must integrate two disparate signals, the spoken language and the visual context, in support of action (e.g., complex movements of the eyes across a scene). We present Impulse Processing, a dynamical systems approach to incremental eye movements in the visual world that suggests a framework for integrating language, vision, and action generally. Our approach assumes that impulses driven by the language and the visual context impinge minutely on a (...) dynamical landscape of attractors corresponding to the potential eye-movement behaviors of the system. We test three unique predictions of our approach in an empirical study in the VWP, and describe an implementation in an artificial neural network. We discuss the Impulse Processing framework in relation to other models of the VWP. (shrink)

Hebbian mechanisms are justified according to their functional utility in an evolutionary sense. The selective advantage of correlating content-contingent stimuli reflects the putative common cause of temporally or spatially contiguous inputs. The selective consequences of such correlations are discussed by using examples from the evolution of signal form in sexual selection and model-mimic coevolution. We suggest that evolutionary justification might be considered in addition to neurophysiology plansibility when constructing representational models.

I argue that intentional psychology does not stand in need of vindication by a lower-level implementation theory from cognitive science, in particular the representational theory of mind (RTM), as most famously Jerry Fodor has argued. The stance of the paper is novel in that I claim this holds even if one, in line with Fodor, views intentional psychology as an empirical theory, and its theoretical posits as as real as those of other sciences. I consider four metaphysical arguments for the (...) idea that intentional psychological states, such as beliefs, must be seen as requiring in-the-head mental representations for us to be able to understand their characteristic causal powers and argue that none of them validly generate their desired conclusions. I go on to argue that RTM, or some computational version thereof, is not motivated by appeal to the nature of cognitive science research either. I conclude that intentional psychology, though an empirical theory, is autonomous from details of lower level mechanism in a way that renders RTM unwarranted. (shrink)

Amit argues that the local neuronal spike rate that persists (reverberating) in the absence of the eliciting stimulus represents the code of the eliciting stimulus. Based on the general argument that the inferred functional meaning of reverberation depends in part on the type of representational assumptions, reverberations may only be important for the encoding of contextual information.

The objective of research in the foundations of Al is to explore such basic questions as: What is a theory in Al? What are the most abstract assumptions underlying the competing visions of intelligence? What are the basic arguments for and against each assumption? In this essay I discuss five foundational issues: (1) Core Al is the study of conceptualization and should begin with knowledge level theories. (2) Cognition can be studied as a disembodied process without solving the symbol grounding (...) problem. (3) Cognition is nicely described in propositional terms. (4) We can study cognition separately from learning. (5) There is a single architecture underlying virtually all cognition. I explain what each of these implies and present arguments from both outside and inside Al why each has been seen as right or wrong. (shrink)