Abstract: A machine learning method and a machine learning device are provided. The machine learning method includes: receiving an input signal and performing normalization on the input signal; transmitting the normalized input signal to a convolutional layer; and adding a sparse coding layer after the convolutional layer, wherein the sparse coding layer uses dictionary atoms to reconstruct signals on a projection of the normalized input signal passing through the convolutional layer, and the sparse coding layer receives a mini-batch input to refresh the dictionary atoms.

Abstract: The present invention provides a method for repairing incomplete 3D depth image using 2D image information. The method includes the following steps: obtaining 2D image information and 3D depth image information; dividing 2D image information into 2D reconstruction blocks and 2D reconstruction boundaries, and corresponding to 3D reconstruction of blocks and 3D reconstruction boundaries; analyzing each 3D reconstruction block, partitioning into residual-surface blocks and repaired blocks; and proceeding at least one 3D image reconstruction, which extends with the initial depth value of the 3D depth image of each of the residual-surface block and covers all the corresponding repaired block to form a repair block and to achieve the purpose of repairing incomplete 3D depth images using 2D image information.

Abstract: The present invention provides a method for repairing incomplete 3D depth image using 2D image information. The method includes the following steps: obtaining 2D image information and 3D depth image information; dividing 2D image information into 2D reconstruction blocks and 2D reconstruction boundaries, and corresponding to 3D reconstruction of blocks and 3D reconstruction boundaries; analyzing each 3D reconstruction block, partitioning into residual-surface blocks and repaired blocks; and proceeding at least one 3D image reconstruction, which extends with the initial depth value of the 3D depth image of each of the residual-surface block and covers all the corresponding repaired block to form a repair block and to achieve the purpose of repairing incomplete 3D depth images using 2D image information.

Abstract: A machine learning method and a machine learning device are provided. The machine learning method includes: receiving an input signal and performing normalization on the input signal; transmitting the normalized input signal to a convolutional layer; and adding a sparse coding layer after the convolutional layer, wherein the sparse coding layer uses dictionary atoms to reconstruct signals on a projection of the normalized input signal passing through the convolutional layer, and the sparse coding layer receives a mini-batch input to refresh the dictionary atoms.

Abstract: A source separation method and a source separation device are provided. The source separation method comprises: obtaining at least two source time-frequency signals and a mixed time-frequency signal of the at least two source time-frequency signals; disposing the mixed time-frequency signal at an input layer of a complex-valued deep neural network, and taking the at least two time-frequency signals as a target of the complex-valued deep neural network; calculating a cost function of the complex-valued deep neural network; and performing partial differential to a real part and an imaginary part of a network parameter of the complex-valued deep neural network respectively to minimize the cost function.

Abstract: An integration device and an integration method thereof are provided. The integration device includes a storage and a processor. The storage stores a first database which includes a plurality of first artifacts. The processor accesses the first database and a second database, and compares each second artifact of the second database with the first artifacts to update the first database.

Abstract: An integration device and an integration method thereof are provided. The integration device executes an artifact integration procedure to integrate the artifacts in a first database and the artifacts in the second database. Based on the access authority of each process role in the first database and the access authority of each process role added from the second database into the first database, the integration device further modifies a plurality of application programming interfaces associated with the integrated artifacts and modifies a plurality of processes according to the modified application programming interfaces. In addition, the integration device further executes a process role integration procedure to integrate the process roles of the first database and the process roles added from the second database into the first database.

Abstract: An integration device and an integration method thereof are provided. The integration device executes an artifact integration procedure to integrate the artifacts in a first database and the artifacts in the second database. Based on the access authority of each process role in the first database and the access authority of each process role added from the second database into the first database, the integration device further modifies a plurality of application programming interfaces associated with the integrated artifacts and modifies a plurality of processes according to the modified application programming interfaces. In addition, the integration device further executes a process role integration procedure to integrate the process roles of the first database and the process roles added from the second database into the first database.

Abstract: An integration device and an integration method thereof are provided. The integration device includes a storage and a processor. The storage stores a first database which includes a plurality of first artifacts. The processor accesses the first database and a second database, and compares each second artifact of the second database with the first artifacts to update the first database.