293 citations · 845 across the 45 of their papers we have counts for
50 papers
On the Natural Gradient of the Evidence Lower Bound
Nihat Ay, Jesse van Oostrum, Adwait Datar
This article studies the Fisher-Rao gradient, also referred to as the natural gradient, of the evidence lower bound (ELBO) which plays a central role in generative machine learning…
Inversion of Bayesian Networks
Jesse van Oostrum, Peter van Hintum, Nihat Ay
Variational autoencoders and Helmholtz machines use a recognition network (encoder) to approximate the posterior distribution of a generative model (decoder). In this paper we stud…
Outsourcing Control requires Control Complexity
Carlotta Langer, Nihat Ay
An embodied agent constantly influences its environment and is influenced by it. We use the sensorimotor loop to model these interactions and thereby we can quantify different info…
Invariance Properties of the Natural Gradient in Overparametrised Systems
Jesse van Oostrum, Johannes Müller, Nihat Ay
The natural gradient field is a vector field that lives on a model equipped with a distinguished Riemannian metric, e.g. the Fisher-Rao metric, and represents the direction of stee…
How Morphological Computation shapes Integrated Information in Embodied Agents
Carlotta Langer, Nihat Ay
The Integrated Information Theory provides a quantitative approach to consciousness and can be applied to neural networks. An embodied agent controlled by such a network influences…
Approaching a large deviation theory for complex systems
Ugur Tirnakli, Constantino Tsallis, Nihat Ay
The standard Large Deviation Theory (LDT) is mathematically illustrated by the Boltzmann-Gibbs factor which describes the thermal equilibrium of short-range-interacting many-body H…