Browsing by Author "Denis-le Coarer, Florian"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A power-efficient architecture for silicon photonic reservoir computing
    (EU project PHRESCO, 2009) Sackesyn, Stijn; Ma, Chonghuai; Katumba, Andrew; Denis-le Coarer, Florian; Dambre, Joni; Bienstman, Peter
    Reservoir computing is a machine learning technique in which a nonlinear dynamical system which is also called the reservoir is used for computation. While it was originally implemented as an efficient way to train a neural network [1], it has now grown to a method which is commonly used for classification and regression tasks. Unlike other techniques which optimize the recurrent neural network (RNN) itself to solve a task, the RNN is not modified during training in reservoir computing. Instead, a linear combination is used to train an optimal classifier in the high dynamical state space to which the signal is projected by propagation through the reservoir. By keeping the recurrent network unchanged and train only on the level of the linear output layer makes reservoir computing a computationally cheap method.
  • Thumbnail Image
    Item
    Threshold plasticity of hybrid Si-VO2 microring resonators
    (Optical Society of America, 2020) Wang, Zhi; Li, Qiang; Fu, Ziling; Katumba, Andrew; Denis-le Coarer, Florian; Rontani, Damien; Sciamanna, Marc; Bienstman, Peter
    We theoretically simulate the threshold plasticity of a high-Q-factor silicon-on-insulator microring resonator integrated with VO2. The proposed structure can perform excitatory and inhibitory learning by tuning the initial working condition.