3 This assumption of the Representational Theory of Thought is controversial. One might think that a person can have the thought that p without having the representation that p. See Cummins 1996. Representations, Targets, and Attitudes. Cambridge, Mass.: MIT Press. 4 We call these schemes "classical" in what follows (one could also call them "tarskian"). See

No abstract

No abstract

IIT includes commitments about the very nature of physical reality, a fact both highly unusual for an empirical theory within neuroscience, and surprisingly underappreciated within the literature. These commitments are intimately tied to the theory; they are not incidental. This paper demonstrates as much by raising certain objections in a “naive” way, and then exposing how the principled IIT responses would rely upon metaphysical positions. Along the way we draw on the IIT literature for support for these interpretations, but also point to a need for elaboration and clarification. Section 1 applies the Placement Argument in a way that leads to problem involving zombies, treated in Section 2. Section 3 frames the zombie problem as an apparent dilemma, and addresses that dilemma by drawing on claims in the IIT literature concerning physical reality. Section 4 raises a related dilemma and treats it in a way that dovetails with the treatment in Section 3 of physical reality. All of this underscores not just the breadth of IIT, but the relevance of this breadth to a full consideration of IIT’s merits.

We argue that atomistic learning-learning that requires training only on a novel item to be learned-is problematic for networks in which every weight is available for change in every learning situation. This is potentially significant because atomistic learning appears to be commonplace in humans and most non-human animals. We briefly review various proposed fixes, concluding that the most promising strategy to date involves training on pseudo-patterns along with novel items, a form of learning that is not strictly atomistic, but which looks very much like it 'from the outside'. The ProblemThe assumption that we have the ability to evaluate and add or delete beliefs individually is common in the psychological literature on memory, concept acquisition, and language acquisition (Ramsey, Stitch, & Garon, 1990;Cummins, Poirier, & Roth, 2004). Indeed, this supposition pervades our informal, commonsense framework for understanding the mind, as well as our formal-symbolic models of rationality and epistemology. Rationality, for example, is thought of as at least in part about the management of beliefs and other propositional attitudes: what beliefs we should and should not adopt, when and what to add, when and what to delete, etc. Models of rationality tell us when we ought to revise our individual beliefs, and because ought implies can, these models presuppose that we can manage our beliefs individually. 1At the same time, most of our current connectionist models of cognition suggest that the knowledge used in carrying out many cognitive tasks related to memory,