no code implementations • 23 Nov 2023 • Francesco Mannella, Giovanni Pezzulo
We propose a novel framework that casts TI as a probabilistic preference learning task, using one-parameter Mallows models.
no code implementations • 23 Oct 2023 • Giovanni Pezzulo, Leo D'Amato, Francesco Mannella, Matteo Priorelli, Toon Van de Maele, Ivilin Peev Stoianov, Karl Friston
This paper considers neural representation through the lens of active inference, a normative framework for understanding brain function.
no code implementations • 8 Oct 2023 • Matteo Priorelli, Federico Maggiore, Antonella Maselli, Francesco Donnarumma, Domenico Maisto, Francesco Mannella, Ivilin Peev Stoianov, Giovanni Pezzulo
This article provides a technical illustration of Active Inference models in continuous time and a brief survey of Active Inference models that solve four kinds of control problems; namely, the control of goal-directed reaching movements, active sensing, the resolution of multisensory conflict during movement and the integration of decision-making and motor control.
no code implementations • 14 Aug 2020 • Francesco Mannella
Controlling the internal representation space of a neural network is a desirable feature because it allows to generate new data in a supervised manner.