Propositions: Individuation and Invirtuation

The pressure to individuate propositions more finely than intensionally—that is, hyper-intensionally—has two distinct sources. One source is the philosophy of mind: one can believe a proposition without believing an intensionally equivalent proposition. The second source is metaphysics: there are intensionally equivalent propositions, such that one proposition is true in virtue of the other but not vice versa. I focus on what our theory of propositions should look like when it's guided by metaphysical concerns about what is true in virtue of what. In this paper I articulate and defend a metaphysical theory of the individuation of propositions, according to which two propositions are identical just in case they occupy the same nodes in a network of invirtuation relations. Invirtuation is here taken to be a primitive relation of metaphysical explanation exemplified by propositions that, in conjunction with truth, defines the notion of true in virtue of. After formulating the theory, I compare it with a view that individuates propositions by cognitive equivalence, and then defend the theory from objections.     

Viciousness and Circles of Ground

Metaphysicians of a certain stripe are almost unanimously of the view that grounding is necessarily irreflexive, asymmetric, transitive, and well‐founded. They deny the possibility of circles of ground and, therewith, the possibility of species of metaphysical coherentism. But what's so bad about circles of ground? One problem for coherentism might be that it ushers in anti‐foundationalism: grounding loops give rise to infinite regresses. And this is bad because infinite grounding regresses are vicious. This article argues that circles of ground do not necessarily give rise to infinite regresses, and where they do, those regresses are not necessarily vicious.     

Vector Semiotic Model for Visual Question Answering

In this paper, we propose a Vector Semiotic Model as a possible solution to the symbol grounding problem in the context of Visual Question Answering. The Vector Semiotic Model combines the advantages of a Semiotic Approach implemented in the Sign-Based World Model and Vector Symbolic Architectures. The Sign-Based World Model represents information about a scene depicted on an input image in a structured way and grounds abstract objects in an agent’s sensory input. We use the Vector Symbolic Architecture to represent the elements of the Sign-Based World Model on a computational level. Properties of a high-dimensional space and operations defined for high-dimensional vectors allow encoding the whole scene into a high-dimensional vector with the preservation of the structure. That leads to the ability to apply explainable reasoning to answer an input question. We conducted experiments are on a CLEVR dataset and show results comparable to the state of the art. The proposed combination of approaches, first, leads to the possible solution of the symbol-grounding problem and, second, allows expanding current results to other intelligent tasks (collaborative robotics, embodied intellectual assistance, etc.).