Hossein HosseiniSan Diego, CA

Hossein Hosseini Phones & Addresses

San Diego, CA

Oklahoma City, OK

Education

School / High School: Urmia University 2011 Specialities: M.Sc. in Communication Systems Engineering

Skills

Programming by MATLAB

Mentions for Hossein Hosseini

Hossein Hosseini resumes & CV records

Resumes

Hossein Hosseini Photo 38

Hossein Hosseini

Education:
Urmia University 2011
M.Sc. in Communication Systems Engineering
University of Tabriz 2008
B.Sc. in Electrical Engineering and Electronics
Skills:
Programming by MATLAB

Publications & IP owners

Us Patents

Privacy-Aware Pruning In Machine Learning

US Patent:
2022031, Oct 6, 2022
Filed:
Apr 6, 2021
Appl. No.:
17/223946
Inventors:
- San Diego CA, US
Hossein HOSSEINI - San Diego CA, US
Christos LOUIZOS - Amsterdam, NL
Joseph Binamira SORIAGA - San Diego CA, US
International Classification:
G06F 21/62
G06N 3/08
G06F 17/18
Abstract:
Certain aspects of the present disclosure provide techniques for improved machine learning using private variational dropout. A set of parameters of a global machine learning model is updated based on a local data set, and the set of parameters is pruned based on pruning criteria. A noise-augmented set of gradients is computed for a subset of parameters remaining after the pruning, based in part on a noise value, and the noise-augmented set of gradients is transmitted to a global model server.

Deep Neural Network Model Transplantation Using Adversarial Functional Approximation

US Patent:
2023005, Feb 23, 2023
Filed:
Aug 23, 2021
Appl. No.:
17/409725
Inventors:
- San Diego CA, US
Tijmen Pieter Frederik BLANKEVOORT - Amsterdam, NL
Arash BEHBOODI - Amsterdam, NL
Hossein HOSSEINI - San Diego CA, US
International Classification:
G06N 3/08
G06N 3/04
G06K 9/62
Abstract:
A method for generating an artificial neural network (ANN) model includes initializing weights of a first neural network model. The weight of the first neural network model are updated using adversarial training to approximate a function for predicting an output of a second neural network model.

NOTICE: You may not use PeopleBackgroundCheck or the information it provides to make decisions about employment, credit, housing or any other purpose that would require Fair Credit Reporting Act (FCRA) compliance. PeopleBackgroundCheck is not a Consumer Reporting Agency (CRA) as defined by the FCRA and does not provide consumer reports.