2 papers
cs.LG2024
Dynamical stability and chaos in artificial neural network trajectories along training
Kaloyan Danovski, Miguel C. Soriano, Lucas Lacasa
The process of training an artificial neural network involves iteratively adapting its parameters so as to minimize the error of the network's prediction, when confronted with a le…
quant-ph2024
Optical phase encoding in pulsed approach to reservoir computing
Johan Henaff, Matthieu Ansquer, Miguel C Soriano +3
The exploitation of the full structure of multimode light fields enables compelling capabilities in many fields including classical and quantum information science. We exploit data…