公开(公告)号：GB2583623A

公开(公告)日：2020-11-04

申请号：GB202010475

申请日：2018-12-13

Applicant: IBM

Inventor： RICHARD CHEN ,  QUANFU FAN ,  MARCO PISTOIA ,  TOYOTARO SUZUMURA

IPC: G06N3/08 ,  G06N3/02

Abstract: Techniques facilitating generation of a fused kernel that can approximate a full kernel of a convolutional neural network are provided. In one example, a computer-implemented method comprises determining a first pattern of samples of a first sample matrix and a second pattern of samples of a second sample matrix. The first sample matrix can be representative of a sparse kernel, and the second sample matrix can be representative of a complementary kernel. The first pattern and second pattern can be complementary to one another. The computer- implemented method also comprises generating a fused kernel based on a combination of features of the sparse kernel and features of the complementary kernel that are combined according to a fusing approach and training the fused kernel.

公开(公告)号：GB2496547B

公开(公告)日：2017-05-31

申请号：GB201302244

申请日：2011-07-06

Applicant: IBM

Inventor： LEI DING ,  QUANFU FAN ,  SHARATHCHANDRA UMAPATHIRAO PANKANTI

IPC: G06K9/00 ,  G08B13/196

Abstract: Automated analysis of video data for determination of human behavior includes segmenting a video stream into a plurality of discrete individual frame image primitives which are combined into a visual event that may encompass an activity of concern as a function of a hypothesis. The visual event is optimized by setting a binary variable to true or false as a function of one or more constraints. The visual event is processed in view of associated non-video transaction data and the binary variable by associating the visual event with a logged transaction if associable, issuing an alert if the binary variable is true and the visual event is not associable with the logged transaction, and dropping the visual event if the binary variable is false and the visual event is not associable.