公开(公告)号：US11449803B2

公开(公告)日：2022-09-20

申请号：US16992008

申请日：2020-08-12

Applicant: Intel Corporation

Inventor： Darshan Iyer ,  Nilesh K. Jain

IPC: G06N20/00 ,  G06K9/62 ,  G06K9/00 ,  G06F16/35 ,  G06F17/16 ,  G06N3/063 ,  G06V40/20 ,  G06F16/28

Abstract: Methods, apparatus, and system determine if a data class in a plurality of data classes is separable, such as by determining an average intra-class similarity within each data class, inter-class similarity across all data classes in the plurality of data classes, and determining separability based on the average intra-class similarity relative to the inter-class similarity. Data classes determined to be highly variable may be removed. Pair(s) of data classes not separable from one another may be combined into one class or one of the data classes may be dropped. A hardware accelerator, which may comprise artificial neurons, accelerate performance of the data analysis.

公开(公告)号：US11216749B2

公开(公告)日：2022-01-04

申请号：US16513800

申请日：2019-07-17

Applicant: Intel Corporation

Inventor： Luis S. Kida ,  Nilesh K. Jain ,  Darshan Iyer ,  Ebrahim Al Safadi

IPC: G06N20/00

Abstract: Technologies for platform-targeted machine learning include a computing device to generate a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified and translate the machine learning algorithm model into hardware code for execution on the target platform. The user input is to be classified as being associated with a particular class based on an application of one or more features to the user input, and each of the one or more features has an associated implementation cost indicative of a cost to perform on a target platform on which the corresponding feature is to be applied to the user input.

公开(公告)号：US20210201200A1

公开(公告)日：2021-07-01

申请号：US16992008

申请日：2020-08-12

Applicant: Intel Corporation

Inventor： Darshan Iyer ,  Nilesh K. Jain

IPC: G06N20/00 ,  G06K9/62 ,  G06K9/00

Abstract: Methods, apparatus, and system determine if a data class in a plurality of data classes is separable, such as by determining an average intra-class similarity within each data class, inter-class similarity across all data classes in the plurality of data classes, and determining separability based on the average intra-class similarity relative to the inter-class similarity. Data classes determined to be highly variable may be removed. Pair(s) of data classes not separable from one another may be combined into one class or one of the data classes may be dropped. A hardware accelerator, which may comprise artificial neurons, accelerate performance of the data analysis.

公开(公告)号：US20180189376A1

公开(公告)日：2018-07-05

申请号：US15394711

申请日：2016-12-29

Applicant: Intel Corporation

Inventor： Darshan Iyer ,  Nilesh K. Jain

IPC: G06F17/30 ,  G06N99/00

Abstract: Methods, apparatus, and system determine if a data class in a plurality of data classes is separable, such as by determining an average intra-class similarity within each data class, inter-class similarity across all data classes in the plurality of data classes, and determining separability based on the average intra-class similarity relative to the inter-class similarity. Data classes determined to be highly variable may be removed. Pair(s) of data classes not separable from one another may be combined into one class or one of the data classes may be dropped. A hardware accelerator, which may comprise artificial neurons, accelerate performance of the data analysis.