Graph neural networks (GNNs) enable the analysis of graphs using deep
le...
Probabilistic Graphical Models (PGMs) are generative models of complex
s...
Dynamic graphs with ordered sequences of events between nodes are preval...
We consider the problem of discovering K related Gaussian directed acycl...
Recently, there has been a surge of interest in combining deep learning
...
There is a recent surge of interest in designing deep architectures base...
In this paper, we propose an end-to-end deep learning model, called E2Ef...
Markov Logic Networks (MLNs), which elegantly combine logic rules and
pr...
To better understand and improve the behavior of neural networks, a rece...
Effectively combining logic reasoning and probabilistic inference has be...
Recovering sparse conditional independence graphs from data is a fundame...
We present a particle flow realization of Bayes' rule, where an ODE-base...
The thesis is about an application of the shape optimization to the
morp...
There are great interests as well as many challenges in applying
reinfor...
There are great interests as well as many challenges in applying
reinfor...