Author

M. Trefzer

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jun 2026

Low-power analogue neural networks with trainable nonlinear connections for continuous control

Inspired by Kolmogorov-Arnold networks, trainable nonlinear functions are placed on the connections, making each physical connection a learnable computational element in physical neural networks.

I. Vidamour, F. Aguirre, T. J. Hayward et al. · arXiv.org · 0 citations

Open access Sep 2026

Sliding-window training on readout layer enhances liquid state machines for temporal prediction

It is demonstrated that exposing recent reservoir evolution at the decoder can substantially reduce the limitations of stepwise decoding while retaining the standard reservoir computing protocol.

Shi-Meng Wu, Andrew Walter, Andy M. Tyrrell et al. · npj Unconventional Computing · 0 citations