公开(公告)号：US20190311254A1

公开(公告)日：2019-10-10

申请号：US16448021

申请日：2019-06-21

Applicant: Intel Corporation

Inventor： Javier S. Turek ,  Dipanjan Sengupta ,  Jawad B. Khan ,  Theodore L. Willke

IPC: G06N3/063 ,  G06N3/08 ,  G06T7/11

Abstract: Technologies for performing in-memory training data augmentation for artificial intelligence include a memory comprising media access circuitry connected to a memory media. The media access circuitry is to obtain an input training data set that includes an initial amount of data samples that are usable to train a neural network. The media access circuitry is further to produce, from the input training data set, an augmented training data set with more data samples than the input training data set.

公开(公告)号：US20190135300A1

公开(公告)日：2019-05-09

申请号：US16235917

申请日：2018-12-28

Applicant: Intel Corporation

Inventor： David I. Gonzalez Aguirre ,  Sridhar G. Sharma ,  Javier Felip Leon ,  Javier S. Turek ,  Maria Soledad Elli

IPC: B60W50/02 ,  G05D1/00 ,  G06N3/08 ,  G06N20/00

Abstract: An example includes obtaining first sensor data from a first sensor and second sensor data from a second sensor, the first sensor of a first sensor type different than a second sensor type of the second sensor; generating first encoded sensor data based on the first sensor data and second encoded sensor data based on the second sensor data; generating a contextual fused sensor data representation of the first and second sensor data based on the first and second encoded sensor data; generating first and second reconstructed sensor data based on the contextual fused sensor data representation; determining a deviation estimation based on the first and second reconstructed sensor data, the deviation estimation representative of a deviation between: (a) the first reconstructed sensor data, and (b) the first sensor data; and detecting an anomaly in the deviation estimation, the anomaly indicative of an error associated with the first sensor.

公开(公告)号：US20220114083A1

公开(公告)日：2022-04-14

申请号：US17559755

申请日：2021-12-22

Applicant: Intel Corporation

Inventor： Javier S. Turek ,  Mihai Capotã ,  Parijat Mukherjee ,  Richard Antonello

IPC: G06F11/36

Abstract: Methods, apparatus, systems, and articles of manufacture to generate a surrogate model based on traces from a computing unit are disclosed. An example apparatus includes an interface; instructions; and processor circuitry to execute the instructions to generate sequences of events for a platform; train an artificial intelligence (AI)-based model using the sequences of events; generate a surrogate model based on the trained AI-based model; and perform unit testing using the surrogate model.

公开(公告)号：US11214268B2

公开(公告)日：2022-01-04

申请号：US16235917

申请日：2018-12-28

Applicant: Intel Corporation

Inventor： David I. Gonzalez Aguirre ,  Sridhar G. Sharma ,  Javier Felip Leon ,  Javier S. Turek ,  Maria Soledad Elli

IPC: B60W50/02 ,  G05D1/00 ,  G06N20/00 ,  G06N3/08

Abstract: An example includes obtaining first sensor data from a first sensor and second sensor data from a second sensor, the first sensor of a first sensor type different than a second sensor type of the second sensor; generating first encoded sensor data based on the first sensor data and second encoded sensor data based on the second sensor data; generating a contextual fused sensor data representation of the first and second sensor data based on the first and second encoded sensor data; generating first and second reconstructed sensor data based on the contextual fused sensor data representation; determining a deviation estimation based on the first and second reconstructed sensor data, the deviation estimation representative of a deviation between: (a) the first reconstructed sensor data, and (b) the first sensor data; and detecting an anomaly in the deviation estimation, the anomaly indicative of an error associated with the first sensor.

公开(公告)号：US11810405B2

公开(公告)日：2023-11-07

申请号：US17539083

申请日：2021-11-30

Applicant: Intel Corporation

Inventor： Barath Lakshamanan ,  Linda L. Hurd ,  Ben J. Ashbaugh ,  Elmoustapha Ould-Ahmed-Vall ,  Liwei Ma ,  Jingyi Jin ,  Justin E. Gottschlich ,  Chandrasekaran Sakthivel ,  Michael S. Strickland ,  Brian T. Lewis ,  Lindsey Kuper ,  Altug Koker ,  Abhishek R. Appu ,  Prasoonkumar Surti ,  Joydeep Ray ,  Balaji Vembu ,  Javier S. Turek ,  Naila Farooqui

IPC: G01C22/00 ,  G07C5/00 ,  G05D1/00 ,  G08G1/01 ,  H04L67/12 ,  G06N20/00 ,  G06F9/50 ,  G01C21/34 ,  B60W30/00 ,  G06N3/063 ,  G06N3/084 ,  G06N20/10 ,  G06N3/044 ,  G06N3/045 ,  G08G1/052 ,  G01S19/13 ,  H04L43/0852 ,  G05D1/02 ,  H04L43/16

CPC classification number: G07C5/008 ,  B60W30/00 ,  G01C21/34 ,  G01C21/3415 ,  G01C21/3492 ,  G05D1/0088 ,  G06F9/5027 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063 ,  G06N3/084 ,  G06N20/00 ,  G06N20/10 ,  G08G1/012 ,  H04L67/12 ,  G01S19/13 ,  G05D1/0257 ,  G05D2201/0213 ,  G06F2209/509 ,  G08G1/0112 ,  G08G1/052 ,  H04L43/0852 ,  H04L43/16

Abstract: An autonomous vehicle is provided that includes one or more processors configured to provide a local compute manager to manage execution of compute workloads associated with the autonomous vehicle. The local compute manager can perform various compute operations, including receiving offload of compute operations from to other compute nodes and offloading compute operations to other compute notes, where the other compute nodes can be other autonomous vehicles. The local compute manager can also facilitate autonomous navigation functionality.

公开(公告)号：US11217040B2

公开(公告)日：2022-01-04

申请号：US16383849

申请日：2019-04-15

Applicant: Intel Corporation

Inventor： Barath Lakshamanan ,  Linda L. Hurd ,  Ben J. Ashbaugh ,  Elmoustapha Ould-Ahmed-Vall ,  Liwei Ma ,  Jingyi Jin ,  Justin E. Gottschlich ,  Chandrasekaran Sakthivel ,  Michael S. Strickland ,  Brian T. Lewis ,  Lindsey Kuper ,  Altug Koker ,  Abhishek R. Appu ,  Prasoonkumar Surti ,  Joydeep Ray ,  Balaji Vembu ,  Javier S. Turek ,  Naila Farooqui

IPC: G05D1/00 ,  G07C5/00 ,  G08G1/01 ,  H04W28/08 ,  H04L29/08 ,  G06N20/00 ,  G06F9/50 ,  G01C21/34 ,  B60W30/00 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06N20/10 ,  G08G1/052 ,  G01S19/13 ,  H04L12/26 ,  G05D1/02

Abstract: One embodiment provides for a computing device within an autonomous vehicle, the compute device comprising a wireless network device to enable a wireless data connection with an autonomous vehicle network, a set of multiple processors including a general-purpose processor and a general-purpose graphics processor, the set of multiple processors to execute a compute manager to manage execution of compute workloads associated with the autonomous vehicle, the compute workload associated with autonomous operations of the autonomous vehicle, and offload logic configured to execute on the set of multiple processors, the offload logic to determine to offload one or more of the compute workloads to one or more autonomous vehicles within range of the wireless network device.

公开(公告)号：US10332320B2

公开(公告)日：2019-06-25

申请号：US15488914

申请日：2017-04-17

Applicant: Intel Corporation

Inventor： Barath Lakshamanan ,  Linda L. Hurd ,  Ben J. Ashbaugh ,  Elmoustapha Ould-Ahmed-Vall ,  Liwei Ma ,  Jingyi Jin ,  Justin E. Gottschlich ,  Chandrasekaran Sakthivel ,  Michael S. Strickland ,  Brian T. Lewis ,  Lindsey Kuper ,  Altug Koker ,  Abhishek R. Appu ,  Prasoonkumar Surti ,  Joydeep Ray ,  Balaji Vembu ,  Javier S. Turek ,  Naila Farooqui

IPC: G01C22/00 ,  G07C5/00 ,  G05D1/00 ,  G01C21/34 ,  G08G1/01 ,  H04W28/08 ,  G06N20/00 ,  G06F9/50 ,  G08G1/052 ,  G01S19/13 ,  G05D1/02 ,  H04L29/08 ,  H04L12/26

Abstract: One embodiment provides for a computing device within an autonomous vehicle, the compute device comprising a wireless network device to enable a wireless data connection with an autonomous vehicle network, a set of multiple processors including a general-purpose processor and a general-purpose graphics processor, the set of multiple processors to execute a compute manager to manage execution of compute workloads associated with the autonomous vehicle, the compute workload associated with autonomous operations of the autonomous vehicle, and offload logic configured to execute on the set of multiple processors, the offload logic to determine to offload one or more of the compute workloads to one or more autonomous vehicles within range of the wireless network device.