| CPC G06F 18/217 (2023.01) [G06N 3/04 (2013.01); G06N 3/08 (2013.01)] | 14 Claims |
|
1. A data analysis system including a device that analyzes observation data observed by an instrument,
wherein the instrument includes a convertor configured to perform a conversion process of converting the observation data to compression data obtained by compressing the observation data,
the conversion process involves outputting the compression data which is an output of a predetermined intermediate layer obtained as a result of processing the observation data received via an input layer of a learned neural network prepared in advance using portions ranging from the input layer to the intermediate layer,
the device includes an analyzer configured to perform an analysis process of obtaining an analysis result of the observation data from the compression data, the analysis process includes:
inputting the compression data to an intermediate layer subsequent to the predetermined intermediate layer,
inputting data obtained by decoding the compression data, which is an output of the subsequent intermediate layer, to an output layer configured using a Convolutional Neural Network (CNN) model, and
obtaining an analysis result of the observation data as an output of the output layer, and the learned neural network is learned in advance so as to minimize an error between an output of the output layer when observation data of which a true analysis result obtained by the analysis is known is input to the input layer and the true analysis result and an error between the observation data and the decoded data.
|