Ángel Poc-López

Ángel Poc-López
Basque Center for Applied Mathematics

Master of Engineering

About

5
Publications
154
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1
Citation
Additional affiliations
March 2022 - present
Barcelona Supercomputing Center
Position
  • Research Engineer
Description
  • Speech and Natural Language Processing Research Engineer

Publications

Publications (5)
Preprint
Full-text available
Transformer-based models have demonstrated exceptional performance across diverse domains, becoming the state-of-the-art solution for addressing sequential machine learning problems. Even though we have a general understanding of the fundamental components in the transformer architecture, little is known about how they operate or what are their exp...
Chapter
Full-text available
Bayesian theories of biological and brain function speculate that Markov blankets (a conditional independence separating a system from external states) play a key role for facilitating inference-like behaviour in living systems. Although it has been suggested that Markov blankets are commonplace in sparsely connected, nonequilibrium complex systems...
Preprint
Full-text available
Bayesian theories of biological and brain function speculate that Markov blankets (a conditional independence separating a system from external states) play a key role for facilitating inference-like behaviour in living systems. Although it has been suggested that Markov blankets are commonplace in sparsely connected, nonequilibrium complex systems...
Chapter
We extend previous mean-field approaches for non-equilibrium neural network models to estimate correlations in the system. This offers a powerful tool for approximating the system dynamics, as well as a fast method for inferring network parameters from observations. We develop our method for the asymmetric kinetic Ising model and test its performan...
Preprint
Full-text available
We extend previous mean-field approaches for non-equilibrium neural network models to estimate correlations in the system. This offers a powerful tool for approximating the system dynamics as well as a fast method to infer network parameters from observations. We develop our method in an asymmetric kinetic Ising model and test its performance on 1)...

Network

Cited By