Method and device with reservoir management and neural network online learning

A reservoir management device comprising:

• a memory configured to store a reservoir including a plurality of sets of labeled sample data;
• and
• a processor configured to:
• in response to receiving input data to which label information is mapped, determine whether to add the input data to the reservoir based on a sampling probability;
• and
• in response to determining to add the input data to the reservoir when the reservoir is filled, select candidate data to be removed from among the sets of sample data included in the reservoir based on a target label distribution and a current label distribution of the reservoir, and remove the selected candidate data from the reservoir.

A mobile terminal comprising:

• a receiver configured to receive a data stream including input data to which label information is mapped;
• a memory configured to store a reservoir including a plurality of sets of labeled sample data and a neural network model;
• and
• a processor configured to:
• in response to receiving the input data to which the label information is mapped, determine whether to add the input data to the reservoir based on a sampling probability;
• in response to determining to add the input data to the reservoir when the reservoir is filled, select candidate data to be removed from among the sets of sample data included in the reservoir based on a target label distribution and a current label distribution of the reservoir, and remove the selected candidate data from the reservoir;
• and
• train the neural network model using sample data of the reservoir from which the selected candidate data is removed.