Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Reservoir computing in simulated neuronal cultures: Effect of network structure

  • Mats Houben, Akke
  • Haeb, Anna-Christina
  • Garcia Ojalvo, Jordi
  • Soriano i Fradera, Jordi
Biological neurons are emerging as attractive candidates for artificial intelligence and machine learning applications given their natural energy efficiency and self-repair capacity. However, they differ from their idealized artificial counterparts. Biological neurons have highly variable and noisy dynamics and display intrinsic spontaneous activity instead of purely input-driven dynamics. Moreover, biological neuronal networks have physically constrained and highly plastic connections, leading to a complex and ever evolving connectivity structure. Here, we investigate (numerically and with preliminary experimental data) the stability of the input responses of neuronal cultures using a reservoir computing framework. Utilizing a numerical model for the growth and activity of neuronal cultures, previously used to model experimental data, we investigate the effect of large-scale network topology, specifically homogeneous vs modular architectures, on fading memory, reservoir performance under increasingly noisy dynamics, and robustness to network rewiring. We find that modular networks exhibit longer fading memory time, sustain higher performance under noisy conditions, and are more robust to connectivity rewiring than homogeneous networks. Finally, we observe no relationship between some characteristics of the network adjacency matrix (specifically its spectral properties) and reservoir computing performance., This research was supported by the European Union Horizon 2020 research and innovation program under Grant No. 964877 (project NEU-CHiP). We also acknowledge financial support from the Spanish Ministerio de Ciencia e Innovación under Project Nos. PID2022-137713NB-C22 and PID2024-160263NB-I00, funded by MCIU/AEI/10.13039/501100011033 and by ERDF/EU, and by the Generalitat de Catalunya under Project No. 2021-SGR-00450. J.G.O. acknowledges financial support from the European Research Council, under Synergy Grant No. 101167121 (CeLEARN).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Reinforcement learning in densely recurrent biological networks

  • Churchland, Miles Walter
  • Garcia Ojalvo, Jordi
Training highly recurrent networks is a technical challenge: gradient-based methods suffer from exploding or vanishing gradients, while purely evolutionary searches converge slowly. We introduce a hybrid, gradient-free optimization framework that implements reinforcement learning by coupling global evolutionary exploration with local direct search exploitation. The method, termed ENOMAD (Evolutionary Nonlinear Optimization with Mesh Adaptive Direct search), is benchmarked on a suite of food-foraging tasks instantiated in the fully mapped neural connectome of the nematode Caenorhabditis elegans. Crucially, ENOMAD leverages biologically derived weight priors, letting it refine-rather than rebuild the organism's native circuitry. The resulting network significantly over-performs the untrained connectome, in what can be interpreted as an example of transfer learning. Our findings demonstrate that integrating evolutionary search with nonlinear optimization provides an efficient, biologically grounded strategy for specializing natural recurrent networks toward a specified set of tasks., This work was supported by the Ministerio de Ciencia, Innovación y Universidades and the Agencia Estatal de Innovación / FEDER (Spain) under project PID2024-160263NB-I00, and by the European Research Council, under Synergy grant 101167121 (CeLEARN). M.W.C. was supported by a Summer Internship Award from the Center for Life Beyond Reed (CLBR). We thank Anne Churchland, Gabriel Torregrosa, Raul de Palma, and the members of UPF’s Dynamical Systems Biology lab for crucial insights and feedback throughout the project. Additionally, we are grateful to the Barcelona Program for Interdisciplinary Studies (BaPIS) at Pompeu Fabra University, for bringing us together to work on this project. We finally wish to acknowledge the scientific, mathematical, and computational communities whose advancements have made this project possible.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Reinforcement learning in densely recurrent biological networks

  • Churchland, Miles Walter
  • Garcia Ojalvo, Jordi
Training highly recurrent networks is a technical challenge: gradient-based methods suffer from exploding or vanishing gradients, while purely evolutionary searches converge slowly. We introduce a hybrid, gradient-free optimization framework that implements reinforcement learning by coupling global evolutionary exploration with local direct search exploitation. The method, termed ENOMAD (Evolutionary Nonlinear Optimization with Mesh Adaptive Direct search), is benchmarked on a suite of food-foraging tasks instantiated in the fully mapped neural connectome of the nematode Caenorhabditis elegans. Crucially, ENOMAD leverages biologically derived weight priors, letting it refine-rather than rebuild the organism's native circuitry. The resulting network significantly over-performs the untrained connectome, in what can be interpreted as an example of transfer learning. Our findings demonstrate that integrating evolutionary search with nonlinear optimization provides an efficient, biologically grounded strategy for specializing natural recurrent networks toward a specified set of tasks., This work was supported by the Ministerio de Ciencia, Innovación y Universidades and the Agencia Estatal de Innovación / FEDER (Spain) under project PID2024-160263NB-I00, and by the European Research Council, under Synergy grant 101167121 (CeLEARN). M.W.C. was supported by a Summer Internship Award from the Center for Life Beyond Reed (CLBR). We thank Anne Churchland, Gabriel Torregrosa, Raul de Palma, and the members of UPF’s Dynamical Systems Biology lab for crucial insights and feedback throughout the project. Additionally, we are grateful to the Barcelona Program for Interdisciplinary Studies (BaPIS) at Pompeu Fabra University, for bringing us together to work on this project. We finally wish to acknowledge the scientific, mathematical, and computational communities whose advancements have made this project possible.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Reservoir computing in simulated neuronal cultures: Effect of network structure

  • Mats Houben, Akke
  • Haeb, Anna-Christina
  • Garcia Ojalvo, Jordi
  • Soriano i Fradera, Jordi
Biological neurons are emerging as attractive candidates for artificial intelligence and machine learning applications given their natural energy efficiency and self-repair capacity. However, they differ from their idealized artificial counterparts. Biological neurons have highly variable and noisy dynamics and display intrinsic spontaneous activity instead of purely input-driven dynamics. Moreover, biological neuronal networks have physically constrained and highly plastic connections, leading to a complex and ever evolving connectivity structure. Here, we investigate (numerically and with preliminary experimental data) the stability of the input responses of neuronal cultures using a reservoir computing framework. Utilizing a numerical model for the growth and activity of neuronal cultures, previously used to model experimental data, we investigate the effect of large-scale network topology, specifically homogeneous vs modular architectures, on fading memory, reservoir performance under increasingly noisy dynamics, and robustness to network rewiring. We find that modular networks exhibit longer fading memory time, sustain higher performance under noisy conditions, and are more robust to connectivity rewiring than homogeneous networks. Finally, we observe no relationship between some characteristics of the network adjacency matrix (specifically its spectral properties) and reservoir computing performance., This research was supported by the European Union Horizon 2020 research and innovation program under Grant No. 964877 (project NEU-CHiP). We also acknowledge financial support from the Spanish Ministerio de Ciencia e Innovación under Project Nos. PID2022-137713NB-C22 and PID2024-160263NB-I00, funded by MCIU/AEI/10.13039/501100011033 and by ERDF/EU, and by the Generalitat de Catalunya under Project No. 2021-SGR-00450. J.G.O. acknowledges financial support from the European Research Council, under Synergy Grant No. 101167121 (CeLEARN).