Zobrazeno 1 - 10
of 357
pro vyhledávání: '"P. Clere"'
Autor:
Smithe, Toby St Clere
In probabilistic modelling, joint distributions are often of more interest than their marginals, but the standard composition of stochastic channels is defined by marginalization. Recently, the notion of 'copy-composition' was introduced in order to
Externí odkaz:
http://arxiv.org/abs/2406.08286
Autor:
Smithe, Toby St Clere
We introduce structured active inference, a large generalization and formalization of active inference using the tools of categorical systems theory. We cast generative models formally as systems "on an interface", with the latter being a composition
Externí odkaz:
http://arxiv.org/abs/2406.07577
We present a categorical formulation of the cognitive frameworks of Predictive Processing and Active Inference, expressed in terms of string diagrams interpreted in a monoidal category with copying and discarding. This includes diagrammatic accounts
Externí odkaz:
http://arxiv.org/abs/2308.00861
Publikováno v:
Annals of Intensive Care, Vol 14, Iss 1, Pp 1-3 (2024)
Externí odkaz:
https://doaj.org/article/5273f5cf8ac94f5c8816a8731c0cc62b
Autor:
Smithe, Toby St Clere
Publikováno v:
EPTCS 397, 2023, pp. 279-298
We characterize a number of well known systems of approximate inference as loss models: lax sections of 2-fibrations of statistical games, constructed by attaching internally-defined loss functions to Bayesian lenses. Our examples include the relativ
Externí odkaz:
http://arxiv.org/abs/2306.17009
Bayes' rule tells us how to invert a causal process in order to update our beliefs in light of new evidence. If the process is believed to have a complex compositional structure, we may observe that the inversion of the whole can be computed piecewis
Externí odkaz:
http://arxiv.org/abs/2305.06112
Autor:
Smithe, Toby St Clere
This dissertation reports some first steps towards a compositional account of active inference and the Bayesian brain. Specifically, we use the tools of contemporary applied category theory to supply functorial semantics for approximate inference. To
Externí odkaz:
http://arxiv.org/abs/2212.12538
Autor:
Friston, Karl J, Ramstead, Maxwell J D, Kiefer, Alex B, Tschantz, Alexander, Buckley, Christopher L, Albarracin, Mahault, Pitliya, Riddhi J, Heins, Conor, Klein, Brennan, Millidge, Beren, Sakthivadivel, Dalton A R, Smithe, Toby St Clere, Koudahl, Magnus, Tremblay, Safae Essafi, Petersen, Capm, Fung, Kaiser, Fox, Jason G, Swanson, Steven, Mapes, Dan, René, Gabriel
Publikováno v:
Collective Intelligence, 3(1), 2024
This white paper lays out a vision of research and development in the field of artificial intelligence for the next decade (and beyond). Its denouement is a cyber-physical ecosystem of natural and synthetic sense-making, in which humans are integral
Externí odkaz:
http://arxiv.org/abs/2212.01354
Autor:
Smithe, Toby St Clere
Publikováno v:
EPTCS 372, 2022, pp. 133-148
We extend our earlier work on the compositional structure of cybernetic systems in order to account for the embodiment of such systems. All their interactions proceed through their bodies' boundaries: sensations impinge on their surfaces, and actions
Externí odkaz:
http://arxiv.org/abs/2211.01831
Autor:
Smithe, Toby St. Clere
We develop the compositional theory of active inference by introducing activity, functorially relating statistical games to the dynamical systems which play them, using the new notion of approximate inference doctrine. In order to exhibit such functo
Externí odkaz:
http://arxiv.org/abs/2208.12173