research
∙
07/20/2023
On the Fisher-Rao Gradient of the Evidence Lower Bound
This article studies the Fisher-Rao gradient, also referred to as the na...
share
research
∙
12/20/2022
Inversion of Bayesian Networks
Variational autoencoders and Helmholtz machines use a recognition networ...
research
∙
09/03/2022
Learning to Predict Requires Integrated Information
Embodied agents are regularly faced with the challenge to learn new task...
research
∙
06/30/2022
Invariance Properties of the Natural Gradient in Overparametrised Systems
The natural gradient field is a vector field that lives on a model equip...
research
∙
08/02/2021
How Morphological Computation shapes Integrated Information in Embodied Agents
The Integrated Information Theory provides a quantitative approach to co...
research
∙
08/26/2020
Complexity as Causal Information Integration
Complexity measures in the context of the Integrated Information Theory ...
research
∙
08/15/2020
Natural Wake-Sleep Algorithm
The benefits of using the natural gradient are well known in a wide rang...
research
∙
07/06/2020
Confounding Ghost Channels and Causality: A New Approach to Causal Information Flows
Information theory provides a fundamental framework for the quantificati...
research
∙
05/23/2020
The information-geometric perspective of Compositional Data Analysis
Information geometry uses the formal tools of differential geometry to d...
research
∙
05/21/2020
On the Locality of the Natural Gradient for Deep Learning
We study the natural gradient method for learning in deep Bayesian netwo...
research
∙
10/14/2019
Information Decomposition based on Cooperative Game Theory
We offer a new approach to the information decomposition problem in info...
research
∙
06/29/2017
Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines
In the past three decades, many theoretical measures of complexity have ...
research
∙
05/31/2016
Information Theoretically Aided Reinforcement Learning for Embodied Agents
Reinforcement learning for embodied agents is a challenging problem. The...
research
∙
12/01/2015
Evaluating Morphological Computation in Muscle and DC-motor Driven Models of Human Hopping
In the context of embodied artificial intelligence, morphological comput...
research
∙
03/24/2015
Geometry and Determinism of Optimal Stationary Control in Partially Observable Markov Decision Processes
It is well known that for any finite state Markov decision process (MDP)...
research
∙
02/14/2014
Geometry and Expressive Power of Conditional Restricted Boltzmann Machines
Conditional restricted Boltzmann machines are undirected stochastic neur...
research
∙
03/01/2013
Maximal Information Divergence from Statistical Models defined by Neural Networks
We review recent results about the maximal values of the Kullback-Leible...
research
∙
01/29/2013
Quantifying Morphological Computation
The field of embodied intelligence emphasises the importance of the morp...
research
∙
10/11/2009