公开(公告)号：US11544607B2

公开(公告)日：2023-01-03

申请号：US16417192

申请日：2019-05-20

Applicant: Wisconsin Alumni Research Foundation

Inventor： Haoliang Sun ,  Ronak R. Mehta ,  Hao Zhou ,  Vikas Singh ,  Vivek Prabhakaran ,  Stirling C. Johnson

IPC: G06N7/00 ,  G06F17/18 ,  G06N20/20 ,  G06N3/08 ,  G06N3/04

Abstract: A machine learning architecture employs two machine learning networks that are joined by a statistical model allowing the imposition of a predetermined statistical model family into a learning process in which the networks translate between and data types. For example, the statistical model may enforce a Gaussian conditional probability between the latent variables in the translation process. In one application, MRI images may be translated into PET images with reduced mode collapse, blurring, or other “averaging” type behaviors.

公开(公告)号：US20200065648A1

公开(公告)日：2020-02-27

申请号：US16107382

申请日：2018-08-21

Applicant: Wisconsin Alumni Research Foundation

Inventor： Seong Jae Hwang ,  Ronak R. Mehta ,  Vikas Singh

IPC: G06N3/04 ,  G06N3/08

Abstract: A neural net processor provides twin processing paths trainable using different moments of the input data, one moment providing a proxy for uncertainty. Subsequent operation of the trained neural net allows monitoring of the uncertainty proxy to provide real-time assessment of neural net model-based uncertainty.

公开(公告)号：US11537846B2

公开(公告)日：2022-12-27

申请号：US16107382

申请日：2018-08-21

Applicant: Wisconsin Alumni Research Foundation

Inventor： Seong Jae Hwang ,  Ronak R. Mehta ,  Vikas Singh

IPC: G06N3/08 ,  G06N3/04

Abstract: A neural net processor provides twin processing paths trainable using different moments of the input data, one moment providing a proxy for uncertainty. Subsequent operation of the trained neural net allows monitoring of the uncertainty proxy to provide real-time assessment of neural net model-based uncertainty.

公开(公告)号：US20200372384A1

公开(公告)日：2020-11-26

申请号：US16417192

申请日：2019-05-20

Applicant: Wisconsin Alumni Research Foundation

Inventor： Haoliang Sun ,  Ronak R. Mehta ,  Hao Zhou ,  Vikas Singh ,  Vivek Prabhakaran ,  Stirling C. Johnson

IPC: G06N7/00 ,  G06N20/20 ,  G06F17/18

Abstract: A machine learning architecture employs two machine learning networks that are joined by a statistical model allowing the imposition of a predetermined statistical model family into a learning process in which the networks translate between and data types. For example, the statistical model may enforce a Gaussian conditional probability between the latent variables in the translation process. In one application, MRI images may be translated into PET images with reduced mode collapse, blurring, or other “averaging” type behaviors.