8 papers
Free-Probability Kernels for Zero-Rollout Hyperparameter Selection in Reservoir Computing
Sara Malacarne, Andrea Ceni, Claudio Gallicchio
Reservoir computing (RC) couples a fixed recurrent dynamical system with a trained lightweight readout, but this efficiency is partly lost during hyperparameter selection: the recu…
Frequency Domain Reservoir Computing
Klaus Schertler, Xiomara Runge, Andrea Ceni +2
While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requires architectures that balan…
ParalESN: Enabling parallel information processing in Reservoir Computing
Matteo Pinna, Giacomo Lagomarsini, Andrea Ceni +1
Reservoir Computing (RC) has established itself as an efficient paradigm for temporal processing. However, its scalability remains severely constrained by the need to process tempo…
Residual Reservoir Memory Networks
Matteo Pinna, Andrea Ceni, Claudio Gallicchio
We introduce a novel class of untrained Recurrent Neural Networks (RNNs) within the Reservoir Computing (RC) paradigm, called Residual Reservoir Memory Networks (ResRMNs). ResRMN c…
Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling
Andrea Ceni, Alessio Gravina, Claudio Gallicchio +3
The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, exi…
Scalable Memristive-Friendly Reservoir Computing for Time Series Classification
CoÅku Can Horuz, Andrea Ceni, Claudio Gallicchio +1
Memristive devices present a promising foundation for next-generation information processing by combining memory and computation within a single physical substrate. This unique cha…