Search Results for author:
Found 8 papers, 0 papers with code
Understanding Domain-Size Generalization in Markov Logic Networks
This behavior emerges from a lack of internal consistency within an MLN when used across different domain sizes.
Simple and Effective Transfer Learning for Neuro-Symbolic Integration
Then, a NeSy model is trained on the same task via transfer learning, where the weights of the perceptual part are injected from the pretrained network.
Lifted Inference beyond First-Order Logic
We expand a vast array of previous results in discrete mathematics literature on directed acyclic graphs, phylogenetic networks, etc.
Weighted First Order Model Counting with Directed Acyclic Graph Axioms
However, many properties of real-world data can not be modelled in $\mathrm{C^2}$.
Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions
In this paper, we propose Deep Symbolic Learning (DSL), a NeSy system that learns NeSy-functions, i. e., the composition of a (set of) perception functions which map continuous data to discrete symbols, and a symbolic function over the set of symbols.
On Projectivity in Markov Logic Networks
We show that, in terms of data likelihood maximization, RBM is the best possible projective MLN in the two-variable fragment.
Weighted Model Counting in FO2 with Cardinality Constraints and Counting Quantifiers: A Closed Form Formula
Weighted First-Order Model Counting (WFOMC) computes the weighted sum of the models of a first-order logic theory on a given finite domain.
Weighted Model Counting in the two variable fragment with Cardinality Constraints: A Closed Form Formula
We introduce the concept of lifted interpretations as a tool for formulating polynomials for WFOMC.
