no code implementations • 20 Jul 2023 • Nihat Ay, Jesse van Oostrum
This article studies the Fisher-Rao gradient, also referred to as the natural gradient, of the evidence lower bound, the ELBO, which plays a crucial role within the theory of the Variational Autonecoder, the Helmholtz Machine and the Free Energy Principle.
no code implementations • 20 Dec 2022 • 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).
no code implementations • 30 Jun 2022 • 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 steepest ascent of an objective function on the model with respect to this metric.
1 code implementation • 2 Aug 2021 • Carlotta Langer, Nihat Ay
In this article, we combine different methods in order to examine the information flows among and within the body, the brain and the environment of an agent.
1 code implementation • NeurIPS Workshop DL-IG 2020 • Csongor Várady, Riccardo Volpi, Luigi Malagò, Nihat Ay
These models are commonly trained using a two-step optimization algorithm called Wake-Sleep (WS) and more recently by improved versions, such as Reweighted Wake-Sleep (RWS) and Bidirectional Helmholtz Machines (BiHM).
no code implementations • 21 May 2020 • Nihat Ay
We develop the theory for studying the relation between the two versions of the natural gradient and outline a method for the simplification of the natural gradient with respect to the second geometry based on the first one.
no code implementations • 29 Jun 2017 • Maxinder S. Kanwal, Joshua A. Grochow, Nihat Ay
In the past three decades, many theoretical measures of complexity have been proposed to help understand complex systems.
no code implementations • 31 May 2016 • Guido Montufar, Keyan Ghazi-Zahedi, Nihat Ay
Reinforcement learning for embodied agents is a challenging problem.
2 code implementations • 1 Dec 2015 • Keyan Ghazi-Zahedi, Daniel F. B. Haeufle, Guido Montufar, Syn Schmitt, Nihat Ay
An important aspect of morphological computation is that it cannot be assigned to an embodied system per se, but that it is, as we show, behavior- and state-dependent.
no code implementations • 24 Mar 2015 • Guido Montufar, Keyan Ghazi-Zahedi, Nihat Ay
For partially observable Markov decision processes (POMDPs), optimal memoryless policies are generally stochastic.
1 code implementation • 8 Dec 2014 • David Krakauer, Nils Bertschinger, Eckehard Olbrich, Nihat Ay, Jessica C. Flack
We consider biological individuality in terms of information theoretic and graphical principles.
no code implementations • NeurIPS 2011 • Guido Montufar, Johannes Rauh, Nihat Ay
We present explicit classes of probability distributions that can be learned by Restricted Boltzmann Machines (RBMs) depending on the number of units that they contain, and which are representative for the expressive power of the model.
no code implementations • 14 Feb 2014 • Guido Montufar, Nihat Ay, Keyan Ghazi-Zahedi
Conditional restricted Boltzmann machines are undirected stochastic neural networks with a layer of input and output units connected bipartitely to a layer of hidden units.
no code implementations • 26 Sep 2013 • Keyan Zahedi, Georg Martius, Nihat Ay
Previous experiments have shown that the predictive information (PI) is a good candidate to support autonomous, open-ended learning of complex behaviours, because a maximisation of the PI corresponds to an exploration of morphology- and environment-dependent behavioural regularities.
no code implementations • 30 Jan 2013 • Georg Martius, Ralf Der, Nihat Ay
We study nonlinear and nonstationary systems and introduce the time-local predicting information (TiPI) which allows us to derive exact results together with explicit update rules for the parameters of the controller in the dynamical systems framework.
no code implementations • 29 Jan 2013 • Keyan Zahedi, Nihat Ay
We believe that the field would benefit from a formalisation of this concept as we would like to ask how much the morphology and the environment contribute to an embodied agent's behaviour, or how an embodied agent can maximise the exploitation of its morphology within its environment.