Non-transitory computer readable storage medium, mask evaluation method and inspection apparatus

An inspection apparatus, comprising:

• a calculator outputting a calculated value of a post-patterning pattern or of a position or size of a defect in a post-patterning pattern when data representing the circuit pattern of a mask is input, the post-patterning pattern being formed by etching a patterning material by using a resist pattern, the resist pattern being formed by exposing a resist film by using the mask and developing the resist film, the calculator realizing a convolutional neural network, the convolutional neural network having a filter and a weighting coefficient learned to reduce an error of the calculated value and an actual measured value of the post-patterning pattern or of the position or size of the defect using the data and the actual measured value to;
• and
• an inspection unit inspecting a post-patterning pattern formed by etching a patterning material by using a resist pattern, the resist pattern being formed by exposing a resist film by using the mask and developing the resist film.

A mask evaluation method evaluating a mask used to manufacture an integrated circuit device,

• the mask evaluation method comprising calculating a calculated value of second data by inputting first data to a convolutional neural network, the first data corresponding to a circuit pattern of the mask, the second data corresponding to a pattern formed by the mask,
• the convolutional neural network having a filter and a weighting coefficient learned to reduce an error of the calculated value and an actual measured value of the second data by using the first data and the actual measured value.