公开(公告)号：US20190243768A1

公开(公告)日：2019-08-08

申请号：US15891028

申请日：2018-02-07

Applicant: Intel Corporation

Inventor： KSHITIJ DOSHI ,  ROMAN DEMENTIEV ,  VADIM SUKHOMLINOV

IPC: G06F12/0875 ,  G06F9/30

CPC classification number: G06F12/0875 ,  G06F9/30036 ,  G06F9/3004 ,  G06F9/30043 ,  G06F9/30145 ,  G06F9/30178 ,  G06F9/3834 ,  G06F2212/452

Abstract: A processor of an aspect includes a decode unit to decode an instruction. The instruction is to indicate a destination memory address information. An execution unit is coupled with the decode unit. The execution unit, in response to the decode of the instruction, is to store memory addresses, for at least all initial writes to corresponding data items, which are to occur after the instruction in original program order, to a memory address log. A start of the memory address log is to correspond to the destination memory address information. Other processors, methods, systems, and instructions are also disclosed.

公开(公告)号：US20190164057A1

公开(公告)日：2019-05-30

申请号：US16262010

申请日：2019-01-30

Applicant: Intel Corporation

Inventor： KSHITIJ DOSHI

IPC: G06N3/08 ,  G06N3/04

Abstract: Embodiments are directed to mapping and quantification of neural network features for explainable artificial intelligence. An embodiment of one or more storage mediums includes instructions for evaluating contribution of lower level features to higher level features in a neural network, the evaluation including one or more of identification of links between lower level and higher level features, and quantification of contribution of lower level features to higher level features. An embodiment of one or more storage mediums includes instructions for determining support from one or more features for one or more inference decisions by a neural network; determining strength of support for each of the inference decisions; identifying one or more inference decisions with low stability based at least in part on the determined strength of support; and reevaluating the inference decisions that are identified as having low stability.

公开(公告)号：US20230385640A1

公开(公告)日：2023-11-30

申请号：US18323843

申请日：2023-05-25

Applicant: Intel Corporation

Inventor： GLEN J. ANDERSON ,  RAJESH POORNACHANDRAN ,  KSHITIJ DOSHI

IPC: G06N3/08 ,  G06N20/00 ,  G06F16/906 ,  G06F16/901 ,  G06N5/04 ,  G06F18/214 ,  G06F18/40 ,  G06F18/21 ,  G06V10/776 ,  G06V10/778

CPC classification number: G06N3/08 ,  G06N20/00 ,  G06F16/906 ,  G06F16/901 ,  G06N5/04 ,  G06F18/2148 ,  G06F18/41 ,  G06F18/217 ,  G06V10/776 ,  G06V10/7788

Abstract: A mechanism is described for facilitating misuse index for explainable artificial intelligence in computing environments, according to one embodiment. A method of embodiments, as described herein, includes mapping training data with inference uses in a machine learning environment, where the training data is used for training a machine learning model. The method may further include detecting, based on one or more policy/parameter thresholds, one or more discrepancies between the training data and the inference uses, classifying the one or more discrepancies as one or more misuses, and creating a misuse index listing the one or more misuses.

公开(公告)号：US20190197357A1

公开(公告)日：2019-06-27

申请号：US16287313

申请日：2019-02-27

Applicant: Intel Corporation

Inventor： GLEN J. ANDERSON ,  RAJESH POONACHANDRAN ,  KSHITIJ DOSHI

IPC: G06K9/62 ,  G06N20/00 ,  G06N5/04 ,  G06F16/901 ,  G06F16/906

CPC classification number: G06K9/6257 ,  G06F16/901 ,  G06F16/906 ,  G06N5/04 ,  G06N20/00

Abstract: A mechanism is described for facilitating misuse index for explainable artificial intelligence in computing environments, according to one embodiment. A method of embodiments, as described herein, includes mapping training data with inference uses in a machine learning environment, where the training data is used for training a machine learning model. The method may further include detecting, based on one or more policy/parameter thresholds, one or more discrepancies between the training data and the inference uses, classifying the one or more discrepancies as one or more misuses, and creating a misuse index listing the one or more misuses.