Institution profile

Université Libre de Bruxelles

Academic institutioneurope · be
Official website
Research library147linked papers
Opportunities0open roles
Selected work

Representative Papers

Backpropagation as Physical Relaxation: Exact Gradients in Finite Time

Feb 02, 2026

This work addresses the challenge of exactly implementing backpropagation within a physically realizable continuous-time dynamical system in finite time, circumventing the conventional reliance of energy-based models on symmetric weights or asymptotic convergence. By modeling feedforward inference as a continuous process, the authors introduce a non-conservative Lagrangian framework and construct a two-state energy functional encompassing both activations and sensitivities. The saddle-point dynamics of this functional enable simultaneous inference and credit assignment. Crucially, the study provides the first rigorous proof that standard backpropagation can be precisely replicated by a physical relaxation process in at most 2L steps for an L-layer network—without requiring weight symmetry, infinitesimal perturbations, or asymptotic assumptions—thereby enabling exact, finite-time gradient computation and offering a theoretical foundation for brain-inspired and analog hardware implementations.

1 citationsRead paper

Developing Bayesian probabilistic reasoning capacity in HSS disciplines: Qualitative evaluation on bayesvl and BMF analytics for ECRs

Dec 12, 2025arXiv.org

Early-career researchers (ECRs) in the humanities and social sciences often face significant barriers to conducting rigorous complex systems research due to publication pressures, limited resources, and methodological constraints. This work proposes the Bayesian Mindsponge Framework (BMF), which integrates concepts from quantum physics, mathematical logic, and information theory into Bayesian inference through the authors’ custom-developed bayesvl R package and the GITT-VT interdisciplinary analytical paradigm. The resulting ecosystem offers a theory-driven, resource-efficient suite of tools that supports mixed-methods qualitative and quantitative research. Since 2019, this framework has enabled over 160 scholars across 22 countries to publish 112 peer-reviewed articles, substantially lowering the threshold for advanced Bayesian analysis and fostering inclusive, cross-disciplinary methodological innovation.

1 citationsRead paper
Recent publications

Latest Papers