STORAGE DEVICE USING NEURAL NETWORK AND OPERATING METHOD FOR AUTOMATIC REDISTRIBUTION OF INFORMATION AND VARIABLE STORAGE CAPACITY BASED ON ACCURACY-STORAGE CAPACITY TRADEOFF THEREOF

摘要

A memory device using a neural network and an operation method for automatically redistributing information and realizing a variable storage capacity based on the accuracy-storage tradeoff thereof according to various embodiments is to learn input information using a neural network, and learn the learned information. Can be configured to store. According to various embodiments, the neural network includes a plurality of input neurons and a plurality of output neurons, at least one stable synapse and input neurons respectively connecting at least one of the input neurons and at least one of the output neurons. It may include at least one variable synapse that connects the rest of the output neurons and the rest of the output neurons, respectively.