Souvik C Ghosh, 428732 230Th Way NE, Redmond, WA 98053

7571412, Aug 4, 2009

Mar 15, 2006

11/377714

Hung Hing Anthony Pang - San Jose CA, US
Binh Vo - San Jose CA, US
Souvik Ghosh - San Jose CA, US

Altera Corporation - San Jose CA

G06F 17/50

716 12, 716 13, 716 14, 716 15, 716 16, 714724, 714725, 703 14, 703 19

A method for generating automatic design characterization patterns for integrated circuits (IC) is provided. The method includes selecting a routing scheme from a file containing the device description of the routings of the IC. The routing scheme may be of a phase locked loop, clock tree, delay element, or input output block in one embodiment. Resource types for the routing scheme are identified and a path is defined, within constraints, between the resources. Once a path is defined, alternate paths are defined by retracing the path within constraints from an end of the path to the beginning of the path. An alternative path is then built and the alternative path shares a portion of the path previously defined. A computing system providing the functionality of the method is also provided.

2022032, Oct 6, 2022

Mar 31, 2021

17/219482

- Redmond WA, US
Yang CHEN - Sunnyvale CA, US
Jiashuo WANG - Mountain View CA, US
Xiaojing CHEN - Santa Clara CA, US
Chencheng WU - Los Altos CA, US
Souvik GHOSH - Saratoga CA, US
Ankit GUPTA - Fremont CA, US
Jing WANG - Los Altos CA, US
John Patrick MOORE - San Francisco CA, US
Henry Heyburn PISTELL - Ridgewood NJ, US
Mira THAMBIREDDY - San Mateo CA, US
Haowen CAO - Sunnyvale CA, US
Keyi YU - Mountain View CA, US

H04L 29/06
G06N 20/00

Techniques for a flexible data security and machine learning system for merging third-party data are provided. In one technique, the system receives a data set from a third-party entity and receives selection data that indicates that the third-party entity selected a set of data security policies that includes an encryption option and a data mixing option from among multiple data mixing options. In response to receiving the selection data, the system stores data that associates the set of data security policies with the data set, encrypts the data set according to the encryption option, and persistently stores the encrypted data set. Later, the system decrypts the encrypted data set in volatile memory, generates, based on the data mixing option, training data based on the decrypted version of the data set, trains a machine-learned model based on the training data, and stores the machine-learned model in association with the data set.

2020038, Dec 3, 2020

Jun 3, 2019

16/430243

- Redmond WA, US
Kinjal Basu - Stanford CA, US
Wei Lu - San Jose CA, US
Souvik Ghosh - Saratoga CA, US
Mansi Gupta - Pittsburgh PA, US

G06N 20/00
G06N 7/00

In an example embodiment, training data is obtained, the training data comprising values for a plurality of different features. Then a global machine learned model is trained using a first machine learning algorithm by feeding the training data into the first machine learning algorithm during a fixed effect training process. A non-linear first random effects machine learned model is trained by feeding a subset of the training data into a second machine learning algorithm, the subset of the training data being limited to training data corresponding to a particular value of one of the plurality of different features.

2020009, Mar 19, 2020

Sep 19, 2018

16/136007

- San Jose CA, US
Souvik GHOSH - Santa Clara CA, US

H04L 12/813
H04L 12/741
H04L 12/823
H04L 12/851
H04L 12/935

Techniques for monitoring packet telemetry are provided. A policy is received at a first node from a controller, where the policy includes an indication of a first flow. A first packet belonging to the first flow is received at the first node. A second node in a network path for the first packet is determined. A first header is added to the first packet based on the policy, wherein the first header includes an indication of the controller. The first packet is transmitted to the second node. Finally, telemetry data associated with the first node is transmitted to the controller based on the policy.

2020000, Jan 2, 2020

Jun 30, 2018

16/024753

- Redmond WA, US
Guangde Chen - Milpitas CA, US
Curtis Chung-Yen Wang - Mountain View CA, US
Deepak K. Agarwal - Saratoga CA, US
Souvik Ghosh - Saratoga CA, US
Shipeng Yu - Sunnyvale CA, US

G06Q 30/02
G06Q 10/06
G06N 99/00

Machine learning techniques for multi-objective content item selection are provided. In one technique, resource allocation data is stored that indicates, for each campaign of multiple campaigns, a resource allocation amount that is assigned by a central authority. In response to receiving the content request, a subset of the campaigns is identified based on targeting criteria. Multiple scores are generated, each score reflecting a likelihood that a content item of the corresponding campaign will be selected. Based on the scores, a particular campaign from the subset is selected and the corresponding content item transmitted over a computer network to be displayed on a computing device. A resource allocation amount that is associated with the particular campaign is identified. A resource reduction amount associated with displaying the content item of the particular campaign is determined. The particular resource allocation is reduced based on the resource reduction amount.

2019033, Oct 31, 2019

Apr 30, 2018

15/966583

- Redmond WA, US
Souvik Ghosh - Saratoga CA, US
Timothy Paul Jurka - Redwood City CA, US
Shaunak Chatterjee - Sunnyvale CA, US
Wei Xue - Sunnyvale CA, US
Bonnie Barrilleaux - San Francisco CA, US

G06Q 50/00
G06F 17/30
G06F 3/0482
G06F 15/18
G06F 17/18

A plurality of potential feed objects and corresponding identifications of actors who performed a user interface action that caused a corresponding potential feed object to be generated are obtained. The plurality of potential feed objects and corresponding actor identifications are then fed into a machine learned feed object ranking model, with the machine learned feed object ranking model having been trained via a machine learning algorithm to calculate a score for each of the potential feed objects. The score is based on a combination of a likelihood that the user will perform an interaction, via the user interface, on the potential feed object, likelihood that the user's interaction will cause one or more downstream events by other users, and likelihood that a response from a viewer will cause the actor corresponding to the potential feed object to perform an additional user interface action to generate another potential feed object.

2019008, Mar 14, 2019

Sep 11, 2017

15/700652

- Sunnyvale CA, US
Souvik Ghosh - San Jose CA, US
Ying Xuan - Sunnyvale CA, US
Liang Zhang - Fremont CA, US
Deepak Agarwal - Sunnyvale CA, US
Yang Yang - Fremont CA, US

G06F 17/30
G06F 17/11
G06F 7/544

Methods, systems, and computer programs are presented for identifying tuning parameters for mixing items in different categories for a user feed. One method includes maximizing utilities when presenting feeds to social network users, each utility having a weight for mixing items. The method further includes identifying a utilities maximization goal such that a first utility is maximized while other utilities are above a threshold, and initializing a counter. A loop, repeated until convergence, includes generating sample weights; performing an experiment with the sample weights for i users and j feed sessions to determine utility action indicators; for each utility, estimating a posterior distribution of an underlying hyperfunction and drawing samples; for each drawn sample, calculating a utility function and the weight that maximizes the utility function; generating an empirical distribution based on the sample weights; and incrementing the counter. The identified weights are utilized for creating the feeds.

2018026, Sep 13, 2018

Apr 14, 2017

15/488159

- Sunnyvale CA, US
Shilpa Gupta - Mountain View CA, US
Myunghwan Kim - San Jose CA, US
Shaunak Chatterjee - Sunnyvale CA, US
Hema Raghavan - Mountain View CA, US
Souvik Ghosh - San Jose CA, US

G06F 17/30
H04L 29/08

A system, a machine-readable storage medium storing instructions, and a computer-implemented method are described herein are directed to Future Connection Engine that generates a select pairing of member accounts for a potential social network connection. The Future Connection Engine predicts, according to the prediction model, a first number of subsequent social network connections for a first member account in the select pairing that will occur after establishing the potential social network connection and a second number of subsequent social network connections for a second member account in the select pairing that will occur after establishing the potential social network connection. The Future Connection Engine generates connection recommendations for display to the select pairing based on whether the first and/or the second number of subsequent social network connections satisfies a threshold.