Adaptive control of recurrent neural networks using conceptors

no code implementations • 12 May 2024 • Guillaume Pourcel, Mirko Goldmann, Ingo Fischer, Miguel C. Soriano

In a Machine Learning setting, the network's parameters are adapted during a training phase to match the requirements of a given task/problem increasing its computational capabilities.

Learn one size to infer all: Exploiting translational symmetries in delay-dynamical and spatio-temporal systems using scalable neural networks

no code implementations • 5 Nov 2021 • Mirko Goldmann, Claudio R. Mirasso, Ingo Fischer, Miguel C. Soriano

We train these networks to predict the dynamics of delay-dynamical and spatio-temporal systems for a single size.

Deep Time-Delay Reservoir Computing: Dynamics and Memory Capacity

no code implementations • 11 Jun 2020 • Mirko Goldmann, Felix Köster, Kathy Lüdge, Serhiy Yanchuk

We present how the dynamical properties of a deep Ikeda-based reservoir are related to its memory capacity (MC) and how that can be used for optimization.