Antoine Joseph Atallah, Age 4315563 SE 67Th Pl, Bellevue, WA 98006

8428348, Apr 23, 2013

Apr 15, 2009

12/423825

Antoine Atallah - Bellevue WA, US
Alex Weinstein - Seattle WA, US

Microsoft Corporation - Redmond WA

G06K 9/00

382165, 382195, 382224, 382160

Architecture for comparing images by building an initial map from the average color and an inserted blackened area. Accordingly, a map can be built that is more information-rich and smaller, thereby making the system more efficient. The architecture employs a Kohonen neural network (or self-organizing map (SOM)) by guiding the learning of the SOM using characteristics of the images such as average color and a central area. A strong component of the average color of the image and the central area at the approximate center of the image are added to the uninitialized SOM, which allows related colors to converge toward the central area of the image. When input, the SOM organizes the color content of the image on a map, which can be used to compare the image with other images.

2009028, Nov 12, 2009

May 6, 2008

12/115886

Antoine J. Atallah - Bellevue WA, US

Microsoft Corporation - Redmond WA

G06N 3/02

706 18

Methods, systems and computer-readable media for finding similarities between visual objects by evaluating user interactions with a collection of visual objects are provided. Using a neural network, human interactions with a collection of visual objects are evaluated to ascertain relationships or connections between visual objects. The relationship between visual objects indicates that the visual objects are similar. Once relationships between visual objects are identified, a user may select one or more visual objects and receive suggested visual objects that are similar to the one or more visual objects selected by the user.

2010010, Apr 29, 2010

Oct 29, 2008

12/260433

Antoine Joseph Atallah - Bellevue WA, US
Noaa Avital - Seattle WA, US
Alex David Weinstein - Seattle WA, US

Microsoft Corporation - Redmond WA

G06F 17/30
G06F 7/00

707749, 707E17015, 707E1702

Methods, systems, and computer-readable media for finding similarities between visual objects using keywords and computerized visual image analysis are provided. A visual object may be provided as an input. A group of visual objects sharing keywords with the visual object may be generated for further analysis. The visual similarity of this group of visual objects may then be determined using computerized visual analysis. A group of visual objects that have the highest similarity rank, as determined by the computerized visual analysis, may then be displayed.

2013002, Jan 24, 2013

Jul 21, 2011

13/187721

RALF HERBRICH - Cambridge, GB
WILLIAM RAMSEY - Redmond WA, US
ANTOINE ATALLAH - Bellevue WA, US
THORE GRAEPEL - Cambridge, GB
PAUL VIOLA - Redmond WA, US

MICROSOFT CORPORATION - Redmond WA

G06F 17/30

707728, 707E17014

Document features or document ranking values can be associated with a distribution of values. Feature values, feature value coefficients, and/or document ranking values can be generated based on sampled values from the distribution of values. This can allow the relative ranking of a document to vary. As additional information is obtained regarding the document, leading to greater certainty about the appropriate ranking of the document, the width or variation generated by the distribution can be reduced to provide more stable ranking values

2014005, Feb 27, 2014

Aug 24, 2012

13/594685

Ralf Herbrich - Mountain View CA, US
Antoine Joseph Atallah - Bellevue WA, US

G06F 15/16

709217

Processing a prepared update is disclosed. A prepared update associated with a request that has been used by the sender to update a local version of a data associated with the sender is received from a sender. Based at least in part on an identifier included in the prepared update, a selected data handler is selected among a plurality of data handlers. The selected data handler is used to update a centralized version of the data at least in part by using the received prepared update. The centralized version of the data has been previously updated using a plurality of prepared updates received from a plurality of senders. The updated centralized version of the data is sent to update the local version of the data associated with the sender.

2014005, Feb 27, 2014

Aug 24, 2012

13/594690

Ralf Herbrich - Mountain View CA, US
Iouri Y. Poutivski - Cupertino CA, US
Antoine Joseph Atallah - Bellevue WA, US

G06F 15/16

709217

Processing a request is disclosed. A request associated with a first identifier is received. A selected request handler is selected among a first plurality of request handlers to process the request. The selection of the selected request handler is based at least in part on the first identifier. The request is processed using a second identifier included in the request. Processing the request includes using a local version of a data associated with the second identifier and stored in a storage managed by the selected request handler. The local version of the data has been updated using a centralized version of the data. The centralized version of the data has been determined using processing performed by a second plurality of request handlers. The selected request handler is included in the second plurality of request handlers.

2021001, Jan 14, 2021

Sep 21, 2020

17/027599

- Cupertino CA, US
Joshua C. WEINBERG - Sunnyvale CA, US
Joshua R. FORD - Cupertino CA, US
Antoine J. ATALLAH - Bellevue WA, US
Roozbeh MAHDAVIAN - San Francisco CA, US
Eric Lance WILSON - San Jose CA, US

G06F 16/9535
G06F 1/16
G04G 99/00
G06T 19/00
G06N 20/00
G04G 21/02
G04F 10/00
G04G 21/00
G04G 13/02

A system for determining relevant information based on user interactions may include a processor configured to receive data and associated relevance information from a data source and a set of signals describing a current environment of a user or historical user behavior information in which the data source being local to a computing device. The processor may be further configured to provide, using a machine learning model, a relevance score for each of multiple data items based at least in part on the received relevance information and the set of signals. The processor may be further configured to sort the data items based on a ranking of each relevance score for each data item. The processor may be further configured to provide, as output, the multiple data items based at least in part on the ranking.

2018033, Nov 22, 2018

Sep 29, 2017

15/721717

- Cupertino CA, US
Joshua C. Weinberg - Sunnyvale CA, US
Joshua R. Ford - Cupertino CA, US
Antoine J. Atallah - Bellevue WA, US
Roozbeh Mahdavian - San Francisco CA, US
Eric Lance Wilson - San Jose CA, US

G06F 17/30
G06N 99/00
G06T 19/00
G06F 1/16
G04G 99/00

A system for determining relevant information based on user interactions may include a processor configured to receive data and associated relevance information from a data source and a set of signals describing a current environment of a user or historical user behavior information in which the data source being local to a computing device. The processor may be further configured to provide, using a machine learning model, a relevance score for each of multiple data items based at least in part on the received relevance information and the set of signals. The processor may be further configured to sort the data items based on a ranking of each relevance score for each data item. The processor may be further configured to provide, as output, the multiple data items based at least in part on the ranking,