公开(公告)号：US20200302163A1

公开(公告)日：2020-09-24

申请号：US16360006

申请日：2019-03-20

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yixin SHI ,  Aman ORAZAEV ,  Tianyi CHEN ,  Sheng YI

IPC: G06K9/00 ,  G06T7/11 ,  G06N3/04

Abstract: An ink parsing system receives ink strokes at an inking device input and render the received ink strokes into an image in a pixel space. Writing strokes are detected in the image and labeled. Pixels corresponding to the labeled writing strokes are removed from the image. Drawing strokes in the image having the removed pixels are detected using and labeled. Writing objects and drawing objects corresponding, respectively, to the labeled writing strokes and the labeled drawing strokes are output. A digital ink parsing pipeline is thereby provided having accurate ink stroke detection and segmentation.

公开(公告)号：US20200293770A1

公开(公告)日：2020-09-17

申请号：US16355702

申请日：2019-03-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Tianyi CHEN ,  Yixin SHI ,  Sheng YI

IPC: G06K9/00 ,  G06N3/04 ,  G06F17/15

Abstract: A spatially sparse convolutional neural network (CNN) framework is introduced to that leverages high sparsity of input data to significantly reduce the computational cost of applications that employ CNNs (e.g., inking applications and others) by avoiding unnecessary floating point mathematical operations. The framework, which is compatible with parallelized operations, includes (1) a data structure for sparse tensors that both (a) reduces storage burden and (b) speeds computations; (2) a set of sparse tensor operations that accelerate convolution computations; and (3) the merging of pooling and convolutional layers. Practical applications involving handwriting recognition and/or stroke analysis demonstrate a notable reduction in storage and computational burdens.

公开(公告)号：US20230419111A1

公开(公告)日：2023-12-28

申请号：US18458709

申请日：2023-08-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Tianyi CHEN ,  Sheng YI ,  Yixin SHI ,  Xiao TU

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04

Abstract: The performance of a neural network (NN) and/or deep neural network (DNN) can limited by the number of operations being performed as well as management of data among the various memory components of the NN/DNN. A sparsity-inducing regularization optimization process is performed on a machine learning model to generate a compressed machine learning model. A machine learning model is trained using a first set of training data. A sparsity-inducing regularization optimization process is executed on the machine learning model. Based on the sparsity-inducing regularization optimization process, a compressed machine learning model is received. The compressed machine learning model is executed to generate one or more outputs.

公开(公告)号：US20210390384A1

公开(公告)日：2021-12-16

申请号：US16889775

申请日：2020-06-01

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Tianyi CHEN ,  Sheng YI ,  Yixin SHI ,  Xiao TU

IPC: G06N3/08 ,  G06N3/04

Abstract: The performance of a neural network (NN) and/or deep neural network (DNN) can limited by the number of operations being performed as well as management of data among the various memory components of the NN/DNN. A sparsity-inducing regularization optimization process is performed on a machine learning model to generate a compressed machine learning model. A machine learning model is trained using a first set of training data. A sparsity-inducing regularization optimization process is executed on the machine learning model. Based on the sparsity-inducing regularization optimization process, a compressed machine learning model is received. The compressed machine learning model is executed to generate one or more outputs.