Distinct Functional Regime

Distinct functional regimes describe how complex systems exhibit qualitatively different behaviors across varying conditions or parameter settings. Current research focuses on identifying these regimes using data-driven methods, including unsupervised learning, competitive learning with dynamic loss functions, and factor graph models, often coupled with regression techniques or neural network ensembles. This work aims to improve model accuracy and interpretability for systems with non-linear behavior, impacting fields like materials science, neuroscience, and engineering by enabling more precise predictions and optimized designs. The development of robust methods for identifying and modeling these regimes is crucial for understanding and controlling complex systems.

Papers

June 14, 2024

Fundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines
Alberto Fachechi, Elena Agliari, Miriam Aquaro, Anthony Coolen, Menno Mulder
Boltzmann Machine Self Averaging Statistical Mechanical Replica Theory Distinct Functional Regime

May 24, 2024

Discovering deposition process regimes: leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis
Geremy Loachamín Suntaxi, Paris Papavasileiou, Eleni D. Koronaki, Dimitrios G. Giovanis, Georgios Gakis, Ioannis G. Aviziotis, Martin Kathrein, Gabriele Pozzetti, Christoph Czettl, Stéphane P. A. Bordas, Andreas G. Boudouvis
Unsupervised Learning Diffusion Explainer Surrogate Modeling Sensitivity Analysis Spatial Pattern Nuclear Reactor Process Insight Distinct Functional Regime

November 10, 2023

Two-compartment neuronal spiking model expressing brain-state specific apical-amplification, -isolation and -drive regimes
Elena Pastorelli, Alper Yegenoglu, Nicole Kolodziej, Willem Wybo, Francesco Simula, Sandra Diaz, Johan Frederik Storm, Pier Stanislao Paolucci
Full Model Neural Recording Neural State Social Isolation Pyramidal Neuron Distinct Functional Regime

July 19, 2023

A Competitive Learning Approach for Specialized Models: A Solution for Complex Physical Systems with Distinct Functional Regimes
Okezzi F. Ukorigho, Opeoluwa Owoyele
Solution Path Data Driven Model Complex Physical System Dynamic Loss Model Discovery Competitive Learning Distinct Functional Regime

June 6, 2023

Intervention Generalization: A View from Factor Graph Models
Gecia Bravo-Hermsdorff, David S. Watson, Jialin Yu, Jakob Zeitler, Ricardo Silva
Synthetic Data Causal Inference Best View Factor Graph Unmeasured Confounding Distinct Functional Regime

February 24, 2022

Embedded Ensembles: Infinite Width Limit and Operating Regimes
Maksim Velikanov, Roman Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov, Alexey Zaytsev, Dmitry Yarotsky
Ensemble Model Model Ensembling Infinite Width Monte Carlo Dropout Dynamical Regime Independent Model Distinct Functional Regime

Distinct Functional Regime

Papers

Fundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines

Discovering deposition process regimes: leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis

Two-compartment neuronal spiking model expressing brain-state specific apical-amplification, -isolation and -drive regimes

A Competitive Learning Approach for Specialized Models: A Solution for Complex Physical Systems with Distinct Functional Regimes

Intervention Generalization: A View from Factor Graph Models

Embedded Ensembles: Infinite Width Limit and Operating Regimes