公开(公告)号：US11580405B2

公开(公告)日：2023-02-14

申请号：US16727429

申请日：2019-12-26

Applicant: SAP SE

Inventor： Erick David Santillán Perez ,  David Kernert

IPC: G06N3/08 ,  G06N3/084 ,  G06N3/04 ,  G06K9/62

Abstract: Disclosed herein are system, method, and computer program product embodiments for adapting machine learning models for use in additional applications. For example, feature extraction models are readily available for use in applications such as image detection. These feature extraction models can be used to label inputs (such as images) in conjunction with other deep neural network models. However, in adapting the feature extraction models to these uses, it becomes problematic to improve the quality of their results on target data sets, as these feature extraction models are large and resistant to retraining. Approaches disclosed herein include a transfer layer for providing fast retraining of machine learning models.

公开(公告)号：US20170168990A1

公开(公告)日：2017-06-15

申请号：US14966860

申请日：2015-12-11

Applicant: SAP SE

Inventor： David Kernert ,  Wolfgang Lehner ,  Frank Koehler

IPC: G06F17/16

CPC classification number: G06F17/16

Abstract: According to some embodiments, matrix A data may be loaded into a temporary, unordered starting representation that contains coordinates and values for each element of matrix A. Z-curve ordering of matrix A may be performed to create a two-dimensional density map of matrix A by counting matrix elements that are contained in logical two-dimensional block cells of a given size. A quad-tree recursion may be executed on the two-dimensional density map structure in reduced Z-space to identify areas of different densities in the two dimensional matrix space. An adaptive tile matrix representation of input matrix A may then be created. According to some embodiments, an adaptive tile matrix multiplication operation may perform dynamic tile-granular optimization based on density estimates and a cost model.

公开(公告)号：US20190384615A1

公开(公告)日：2019-12-19

申请号：US16010003

申请日：2018-06-15

Applicant: SAP SE

Inventor： David Kernert ,  Simon Seif ,  Boris Gruschko ,  Joachim Fitzer

IPC: G06F9/445 ,  G06F17/30

Abstract: A method for executing a data processing pipeline may be provided. The method may include identifying a file providing a runtime environment required for executing a series of data processing operations comprising the data processing pipeline. The file may be identified based on one or more tags associated with the data processing pipeline. The one or more tags may specify at least one runtime requirement for the series of data processing operations. The file may be executed to generate an executable package that includes a plurality of components required for executing the series of data processing operations. The series of data processing operations included in the data processing pipeline may be executed by at least executing the executable package to provide the runtime environment required for executing the series of data processing operations. Related systems and articles of manufacture, including computer program products, are also provided.

公开(公告)号：US10949219B2

公开(公告)日：2021-03-16

申请号：US16010003

申请日：2018-06-15

Applicant: SAP SE

Inventor： David Kernert ,  Simon Seif ,  Boris Gruschko ,  Joachim Fitzer

IPC: G06F9/445 ,  G06F16/13

Abstract: A method for executing a data processing pipeline may be provided. The method may include identifying a file providing a runtime environment required for executing a series of data processing operations comprising the data processing pipeline. The file may be identified based on one or more tags associated with the data processing pipeline. The one or more tags may specify at least one runtime requirement for the series of data processing operations. The file may be executed to generate an executable package that includes a plurality of components required for executing the series of data processing operations. The series of data processing operations included in the data processing pipeline may be executed by at least executing the executable package to provide the runtime environment required for executing the series of data processing operations. Related systems and articles of manufacture, including computer program products, are also provided.

公开(公告)号：US10061748B2

公开(公告)日：2018-08-28

申请号：US14966860

申请日：2015-12-11

Applicant: SAP SE

Inventor： David Kernert ,  Wolfgang Lehner ,  Frank Koehler

IPC: G06F17/16

CPC classification number: G06F17/16

Abstract: According to some embodiments, matrix A data may be loaded into a temporary, unordered starting representation that contains coordinates and values for each element of matrix A. Z-curve ordering of matrix A may be performed to create a two-dimensional density map of matrix A by counting matrix elements that are contained in logical two-dimensional block cells of a given size. A quad-tree recursion may be executed on the two-dimensional density map structure in reduced Z-space to identify areas of different densities in the two dimensional matrix space. An adaptive tile matrix representation of input matrix A may then be created. According to some embodiments, an adaptive tile matrix multiplication operation may perform dynamic tile-granular optimization based on density estimates and a cost model.