Data sets in the real world are often complex and to some degree hierarchical, with groups
and subgroups of data sharing common characteristics at different levels of abstraction …

Generative models offer a direct way of modeling complex data. Energy-based models
attempt to encode the statistical correlations observed in the data at the level of the …

The recent progresses in Machine Learning opened the door to actual applications of
learning algorithms but also to new research directions both in the field of Machine Learning …

Applications of generative models for genomic data have gained significant momentum in
the past few years, with scopes ranging from data characterization to generation of genomic …

Sampling complex distributions is an important but difficult objective in various fields,
including physics, chemistry, and statistics. An improvement of standard Monte Carlo (MC) …

Parallel learning, namely the simultaneous learning of multiple patterns, constitutes a
modern challenge for neural networks. While this cannot be accomplished by standard …

In this paper, we quantify the impact of using non-convergent Markov chains to train Energy-
Based models (EBMs). In particular, we show analytically that EBMs trained with non …

In this study, we address the challenge of using energy-based models to produce high-
quality, label-specific data in complex structured datasets, such as population genetics, RNA …

In this paper, we quantify the impact of using non-convergent Markov chains to train Energy-
Based models (EBMs). In particular, we show analytically that EBMs trained with non …

Auto-associative neural networks (eg the Hopfield model implementing the standard
Hebbian prescription) serve as a foundational framework for pattern recognition and …