Estimating unknown qubit phase under telegraph noises using recurrent neural network

Abstract We consider a system of qubits affected by an environmental random-telegraph process (RTP) noise and investigate the recently proposed idea using spectator qubit (SQ) as probe to remove effects from data (DQ). By measuring SQ at various times with particular measurement bases, their readouts can be used extract information effects. In this work, we propose use recurrent neural network (RNN), Long short-term memory (LSTM) layers, SQ’s train model estimate errors occurred in DQ. present numerical results DQ’s phases show that LSTM unknown phase estimation accuracy depending on sensitivity.