Dynamical complexity and computation in recurrent neural networks beyond their fixed point - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Scientific Reports Année : 2018

Dynamical complexity and computation in recurrent neural networks beyond their fixed point

Résumé

Spontaneous activity found in neural networks usually results in a reduction of computational performance. As a consequence, artificial neural networks are often operated at the edge of chaos, where the network is stable yet highly susceptible to input information. Surprisingly, regular spontaneous dynamics in Neural Networks beyond their resting state possess a high degree of spatio-temporal synchronization, a situation that can also be found in biological neural networks. Characterizing information preservation via complexity indices, we show how spatial synchronization allows rRNNs to reduce the negative impact of regular spontaneous dynamics on their computational performance.

Dates et versions

hal-02383964 , version 1 (28-11-2019)

Identifiants

Citer

Bicky Marquez, Laurent Larger, Maxime Jacquot, Kouomou Yanne Chembo, Daniel Brunner. Dynamical complexity and computation in recurrent neural networks beyond their fixed point. Scientific Reports, 2018, 8 (1), pp.3319. ⟨10.1038/s41598-018-21624-2⟩. ⟨hal-02383964⟩
17 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More