Abstract: A deep learning-based MLCC stacked alignment inspection system includes an integrated defect detection unit configured to detect core areas requiring inspection of image data in which a stacked structure is photographed from a semiconductor MLCC chip by using at least one deep learning-based core area detection model, perform segmentation in the detected core areas, determine whether a defect exists according to a standard margin percentage range, and enable defect detection by generating normal and/or defective data based on the determination result, a result analysis unit configured to perform visualization for respective results of the core area detection, segmentation, and defect detection of the integrated defect detection unit, and provide stepwise analysis data for the visualized respective results so as to determine whether to modify corresponding data, and a data storage configured to store the normal and/or defective data, and stepwise analysis data.

Abstract: A data classification method and a device thereof for hierarchical multi-label classification are proposed. The data classification device includes an encoder configured to vectorize data, a decoder configured to receive the vectorized data from the encoder, and classification data stored in the decoder, wherein the decoder starts classification of the vectorized data on the basis of a first node in the classification data, allocates a plurality of nodes included in the classification data to the vectorized data, and forms partial layers based on the allocated nodes with respect to the vectorized data, and when terminal nodes or temporary nodes are allocated among the nodes, the decoder ends the allocation to the partial layers to which the terminal nodes or the temporary nodes are allocated and allocates final partial layers formed on the basis of the partial layers to the data.

Abstract: A data classification method and a device thereof for hierarchical multi-label classification are proposed. The data classification device includes an encoder configured to vectorize data, a decoder configured to receive the vectorized data from the encoder, and classification data stored in the decoder, wherein the decoder starts classification of the vectorized data on the basis of a first node in the classification data, allocates a plurality of nodes included in the classification data to the vectorized data, and forms partial layers based on the allocated nodes with respect to the vectorized data, and when terminal nodes or temporary nodes are allocated among the nodes, the decoder ends the allocation to the partial layers to which the terminal nodes or the temporary nodes are allocated and allocates final partial layers formed on the basis of the partial layers to the data.