公开(公告)号：US20190354850A1

公开(公告)日：2019-11-21

申请号：US15982622

申请日：2018-05-17

Applicant: International Business Machines Corporation

Inventor： Patrick Watson ,  Bishwaranjan Bhattacharjee ,  Noel Christopher Codella ,  Brian Michael Belgodere ,  Parijat Dube ,  Michael Robert Glass ,  John Ronald Kender ,  Siyu Huo ,  Matthew Leon Hill

IPC: G06N3/08 ,  G06N5/02 ,  G06N99/00

Abstract: Techniques regarding autonomously facilitating the selection of one or more transfer models to enhance the performance of one or more machine learning tasks are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise an assessment component that can assess a similarity metric between a source data set and a sample data set from a target machine learning task. The computer executable components can also comprise an identification component that can identify a pre-trained neural network model associated with the source data set based on the similarity metric to perform the target machine learning task.

公开(公告)号：US11853877B2

公开(公告)日：2023-12-26

申请号：US16373149

申请日：2019-04-02

Applicant: International Business Machines Corporation

Inventor： Patrick Watson ,  Bishwaranjan Bhattacharjee ,  Siyu Huo ,  Noel Christopher Codella ,  Brian Michael Belgodere ,  Parijat Dube ,  Michael Robert Glass ,  John Ronald Kender ,  Matthew Leon Hill

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04

Abstract: Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be determined. A set of training data based on the cluster can be determined. The new neural network model can be trained based on the set of training data.

公开(公告)号：US20200320379A1

公开(公告)日：2020-10-08

申请号：US16373149

申请日：2019-04-02

Applicant: International Business Machines Corporation

Inventor： Patrick Watson ,  Bishwaranjan Bhattacharjee ,  Siyu Huo ,  Noel Christopher Codella ,  Brian Michael Belgodere ,  Parijat Dube ,  Michael Robert Glass ,  John Ronald Kender ,  Matthew Leon Hill

IPC: G06N3/08 ,  G06N3/04

Abstract: Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be determined. A set of training data based on the cluster can be determined. The new neural network model can be trained based on the set of training data.

公开(公告)号：US20220406454A1

公开(公告)日：2022-12-22

申请号：US17304183

申请日：2021-06-16

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Bo Wen ,  Bing Dang ,  Vince Siu ,  Noel Christopher Codella ,  Erhan Bilal ,  Jeffrey L. Rogers

IPC: G16H40/67 ,  G16H40/40 ,  G16H80/00 ,  G06F30/10 ,  A61B7/04 ,  G09B19/00

Abstract: A method, a structure, and a computer system for enabling telemedicine using printed devices. Exemplary embodiments may include receiving a design for a device and printing the device based on the design using a printer. The exemplary embodiments may further include combining the device with a smart device and utilizing the device to collect data during a telemedicine session administered on the smart device.