Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation

Efficient Uncertainty Propagation for Reinforcement Learning with Limited Data

In a typical reinforcement learning (RL) setting details of the environment are not given explicitly but have to be estimated from observations. Most RL approaches only optimize the expected value. However, if the number of observations is limited considering expected values only can lead to false conclusions. Instead, it is crucial to also account for the estimator’s uncertainties. In this pap...

Interpretable knowledge discovery from data with DC

We present DC* (Double Clustering with A*) as an information granulation method specifically suited for deriving interpretable knowledge from data. DC* is based on two main clustering stages: the first is devoted to compressing multi-dimensional data into few prototypes that grab the main relationships among data; the second is aimed at finding a proper fuzzy granulation of each input feature s...

InterpNET: Neural Introspection for Interpretable Deep Learning

Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable neural networks for classification, inspired by physiological evidence of the human visual system’s inner-workings. This paper proposes a neural network design paradigm, termed InterpNET, which can be combined with any...

Learning of causal relations

To learn about causal relations between variables just by observing samples from them, particular assumptions must be made about those variables’ distributions. This article gives a practical description of how such a learning task can be undertaken based on different possible assumptions. Two categories of assumptions lead to different methods, constraint-based and Bayesian learning, and in ea...

Material for “ On Causal Discovery with Cyclic Additive Noise Models ”