| 摘要 |
<p>An implementation of a reservoir computing based recurrent neural network is disclosed. Cellular automaton is used as the reservoir of dynamical systems. Input is projected onto the initial conditions of automaton cells and nonlinear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the output of the reservoir. The output is further processed according to reservoir computing principles to achieve the assigned task. The reservoir is trained for the specific task and dataset via optimizing the rule of the automaton.</p> |
