Control parameter adjustment device, control parameter adjustment method and computer program

Abstract

The purpose of this invention is to provide a technique that can improve the quality of substrate processing even when the causal relationship between control parameters and the results of substrate processing is not sufficiently clear. The control unit 201 of this invention uses explanatory variable x, intermediate variable f, and target variable y as nodes, and sets the connection relationships between the nodes (connection relationship setting step S332). The control unit 201 uses the dataset of explanatory variable x and intermediate variable f to learn the input-output relationship of intermediate variable f in the network N based on the connection relationships set by the connection relationship setting process S332 (first learning process S333). The control unit 201 uses the dataset of explanatory variable x, intermediate variable f, and target variable z to learn the input-output relationship of the previous target variable z in the network N (second learning process S334). In the second learning process S333, a pre-distribution of induced sparsity is used as the pre-distribution of weight parameters.

Images