Search Results for author:
Found 16 papers, 4 papers with code
On the Fisher-Rao Gradient of the Evidence Lower Bound
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.
Inversion of Bayesian Networks
Variational autoencoders and Helmholtz machines use a recognition network (encoder) to approximate the posterior distribution of a generative model (decoder).
Invariance Properties of the Natural Gradient in Overparametrised Systems
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.
How Morphological Computation shapes Integrated Information in Embodied Agents
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.
Natural Reweighted Wake-Sleep
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).
On the Locality of the Natural Gradient for Deep Learning
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.
Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines
In the past three decades, many theoretical measures of complexity have been proposed to help understand complex systems.
Information Theoretically Aided Reinforcement Learning for Embodied Agents
Reinforcement learning for embodied agents is a challenging problem.
Evaluating Morphological Computation in Muscle and DC-motor Driven Models of Human Hopping
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.
Geometry and Determinism of Optimal Stationary Control in Partially Observable Markov Decision Processes
For partially observable Markov decision processes (POMDPs), optimal memoryless policies are generally stochastic.
The Information Theory of Individuality
We consider biological individuality in terms of information theoretic and graphical principles.
Expressive Power and Approximation Errors of Restricted Boltzmann Machines
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.
Geometry and Expressive Power of Conditional Restricted Boltzmann Machines
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.
Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting: a critical analysis
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.
Information driven self-organization of complex robotic behaviors
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.
Quantifying Morphological Computation
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.
