Yair E Yona

20230068386, Mar 2, 2023

Dec 26, 2020

17/790950

- Santa Clara CA, US
Arjun Anand - Milpitas CA, US
Nageen Himayat - Fremont CA, US
Amir S. Avestimehr - Rancho Palos Verdes CA, US
Ravikumar Balakrishnan - Beaverton OR, US
Prashant Bhardwaj - Sunnyvale CA, US
Jeongsik Choi - San Jose CA, US
Sagar Dhakal - Los Altos CA, US
Brandon Gary Edwards - Portland OR, US
Saurav Prakash - Los Angeles CA, US
Amit Solomon - Cambridge MA, US
Shilpa Talwar - Cupertino CA, US
Yair Eliyahu Yona - Cupertino CA, US

Intel Corporation - Santa Clara CA

G06N 20/00

The apparatus of an edge computing node, a system, a method and a machine-readable medium. The apparatus includes a processor to perform rounds of federated machine learning training including: processing client reports from a plurality of clients of the edge computing network; selecting a candidate set of clients from the plurality of clients for an epoch of the federated machine learning training; causing a global model to be sent to the candidate set of clients; and performing the federated machine learning training on the candidate set of clients. The processor may perform rounds of federated machine learning training including: obtaining coded training data from each of the selected clients; and performing machine learning training on the coded training data.

20210304613, Sep 30, 2021

Apr 9, 2021

17/227191

- Santa Clara CA, US
Yair Yona - Cupertino CA, US
Moreno Ambrosin - Hillsboro OR, US
Xiruo Liu - Portland CA, US
Hosein Nikopour - San Jose CA, US
Shilpa Talwar - Cupertino CA, US
Sridhar Sharma - Palo Alto CA, US
Debabani Choudhury - Thousand Oaks CA, US
Kuilin Clark Chen - Hillsboro OR, US
Jeffrey Ota - Morgan Hill CA, US
Justin Gottschlich - Santa Clara CA, US

G08G 1/00
G01S 5/14
H04W 4/40
G08G 1/052

Methods, apparatus, systems and articles of manufacture are disclosed to validate data communicated by a vehicle. An example apparatus an anomaly detector to, in response to data communicated by a vehicle, at least one of compare an estimated speed with a reported speed or compare a location of the vehicle with a reported location. The apparatus including the anomaly detector further to generate an indication of the vehicle in response to the comparison. The apparatus further includes a notifier to discard data sent by the vehicle and notify surrounding vehicles of the data communicated by the vehicle.

20190220703, Jul 18, 2019

Mar 28, 2019

16/368716

- Santa Clara CA, US
Sagar Dhakal - Los Altos CA, US
Yair Yona - Cupertino CA, US
Nageen Himayat - Fremont CA, US
Shilpa Talwar - Cupertino CA, US

G06K 9/62
G06N 3/08
G06N 20/00
G06F 9/50

Systems, apparatuses, methods, and computer-readable media are provided for load partitioning in distributed machine learning (ML) training using heterogeneous compute nodes in a heterogeneous computing environment, where the heterogeneous compute nodes are connected to a master node via respective wireless links. ML computations are performed by individual heterogeneous compute nodes on respective load partitions. The ML computations are balanced across the heterogeneous compute nodes based on knowledge of respective computational and link parameters of the heterogeneous compute nodes. Other embodiments may be described and/or claimed.

20190215695, Jul 11, 2019

Dec 21, 2018

16/230971

Liuyang Yang - Portland OR, US
Debabani Choudhury - Thousand Oaks CA, US
Sridhar Sharma - Palo Alto CA, US
Justin Gottschlich - Santa Clara CA, US
Zheng Zhang - Portland OR, US
Yair Yona - Cupertino CA, US
Xiruo Liu - Portland OR, US
Moreno Ambrosin - Hillsboro OR, US
Kuilin Clark Chen - Portland OR, US

H04W 12/12
H04W 12/06
H04W 4/40

Methods, apparatus, systems, and articles of manufacture are disclosed to detect attacks in V2X networks. An example apparatus includes a challenge handler to (a) transmit a first challenge packet to a first vehicle to request a transmission of a first response, (b) instruct a second challenge packet to be transmitted to a second vehicle to request a transmission of a second response, (c) increment a first counter when the first response is not obtained, (d) increment a second counter when the second response is not obtained, and (e) after repeating (a)-(d), determine that the first and second vehicles are phantom vehicles associated with an attacker with a half-duplex radio when at least one of the first or second counters satisfy a threshold, and a network interface to instruct a third vehicle associated with the V2X network to ignore future messages from the phantom vehicles based on the determination.

20190130762, May 2, 2019

Dec 27, 2018

16/234495

- Santa Clara CA, US
Yair Yona - Cupertino CA, US
Moreno Ambrosin - Hillsboro OR, US
Xiruo Liu - Portland CA, US
Hosein Nikopour - San Jose CA, US
Shilpa Talwar - Cupertino CA, US
Sridhar Sharma - Palo Alto CA, US
Debabani Choudhury - Thousand Oaks CA, US
Kuilin Clark Chen - Hillsboro OR, US
Jeffrey Ota - Morgan Hill CA, US
Justin Gottschlich - Santa Clara CA, US

G08G 1/00
G08G 1/052
H04W 4/40
G01S 5/14

Methods, apparatus, systems and articles of manufacture are disclosed to validate data communicated by a vehicle. An example apparatus an anomaly detector to, in response to data communicated by a vehicle, at least one of compare an estimated speed with a reported speed or compare a location of the vehicle with a reported location. The apparatus including the anomaly detector further to generate an indication of the vehicle in response to the comparison. The apparatus further includes a notifier to discard data sent by the vehicle and notify surrounding vehicles of the data communicated by the vehicle.