Abstract: A method of reinforcement learning of a neural network device for generating a verification vector for verifying a circuit design comprising a circuit block includes inputting a test vector to the circuit block, generating one or more rewards based on a coverage corresponding to the test vector, the coverage being determined based on a state transition of the circuit block based on the test vector, and applying the one or more rewards to a reinforcement learning.

Abstract: Disclosed are: a three-dimensional flash memory in which the degree of integration in a horizontal direction is improved so as to promote integration; and a manufacturing method therefor. A three-dimensional flash memory according to one embodiment comprises: at least one channel layer extending in one direction; at least one ferroelectric film used as a data storage place while being extended in the one direction so as to encompass the at least one channel layer; and a plurality of electrode layers stacked so as to be vertically connected to the at least one ferroelectric film.

Abstract: Disclosed are: a three-dimensional flash memory in which the degree of integration in a horizontal direction is improved so as to promote integration; and a manufacturing method therefor. A three-dimensional flash memory according to one embodiment comprises: at least one channel layer extending in one direction; at least one ferroelectric film used as a data storage place while being extended in the one direction so as to encompass the at least one channel layer; and a plurality of electrode layers stacked so as to be vertically connected to the at least one ferroelectric film.