Applied Scientist

Amazon

Hi, my name is Gerges (جرجس), which is the arabic pronunciation of Georges, which is the french spelling of George, so everyone calls me George. I currently work as an applied scientist at Amazon, where I have been building and deploying machine learning and forecasting models for AWS workforce planning, and more recently for data center operations. Before joining Amazon, I was at Pacific Northwest National laboratory, doing all things related to Ultrasonics including measurement techniques, modeling and simulation, signal and image processing, machine learning applications for electroencephalograms (EEG). The intersection of computer science, mathematics, and physics is my happy place. When I’m not working, I am trying to get better at them, or out hiking.

Interests

  • Artificial intelligence
  • Time series forecasting
  • Reinforcement learning

Education

  • PhD in Electrical Engineering, 2014

    Michigan State University

  • Masters of Science in Information Networking, 2009

    Carnegie Mellon University

  • BE in Computer and Communication Engineering, 2007

    American University of Beirut

Experience

 
 
 
 
 

Applied Scientist

Amazon

January 2020 – Present Seattle, WA
 
 
 
 
 

Research Scientist

Amazon

February 2019 – January 2020 Seattle, WA
 
 
 
 
 

Research Scientist

Pacific Northwest National Laboratory

August 2017 – September 2018 Richland, WA
 
 
 
 
 

Research Associate

Pacific Northwest National Laboratory

September 2014 – August 2017 Richland, WA
 
 
 
 
 

Intern

Indian Institute of Technology, Madras

May 2010 – July 2010 Chennai, India
 
 
 
 
 

PHD Researcher

Michigan State University

August 2009 – August 2014 East Lansing, MI
 
 
 
 
 

Research assistant

Carnegie Mellon University

August 2008 – May 2009 Pittsburgh, PA
 
 
 
 
 

Intern

University of California at Berkeley

June 2006 – August 2006 Berkeley, CA

Accomplish­ments

Deeplearning.ai Specialization

Coursera Oct 2018

By Andrew Ng

This specialization includes 5 courses:

  • Neural networks and deep learning
  • Improving deep neural networks: Hyperparameter tuning, regularization and optimization
  • Structuring machine learning Projects
  • Convolutional neural Networks
  • Sequence models
See certificate

Deeplearning.ai Bootcamp

Deeplearning.ai Jul 2018 – Jul 2018
I was selected to participate in an intensive 2-day practical deep learning bootcamp organized by deeplearning.ai. We worked in a team of 4 on selecting, training, testing, and demonstrating an object detection detection model. The bootcamp went through all the steps required to build a successful model, starting for understanding client requirements to deploying the model on an android phone.
See certificate

Machine Learning

Coursera Feb 2018

by Andrew Ng

In addition to completing the class, I fully re-wrote the class assignments (starter code + instructions) in python Jupyter notebooks, which allows interested students to submit the assignments using python instead of the native Matlab assignments (this does not apply to students taking class in exchange for a certificate).

Deep Learning (CSCI 497J/597J)

Western Washington University Aug 2017 – Dec 2017
by Brian Hutchinson

CS231n Convolutional Neural Networks for Visual Recognition

Stanford Jun 2017

by Fei-Fei Li, Justin Johnson, and Serena Yeung

Online class audit only (lectures + programming assignments)

The Finite Element Method for Problems in Physics

Coursera Sep 2015
by Krishna Garikipati
See certificate

Previous Projects

*
All Deep Learning Machine Learning Signal Processing Ultrasound NDE

Neural Interactive Machine Learning

Building a brain-computer interface for rapid image labeling

Validation of Ultrasound NDE Simulation Models

Supporting regulatory guides for the nuclear power plant industry in relation to using ultrasound computational models for non-destructive inspection.

Machine Learning and Statistical Signal Processing for Guided Wave Structural Health Monitoring

Building statistical methods to assess damage detection reliability and machine learning models for damage detection

Ultrasound Sensors and Methods for Nuclear Power Plant Environments

Applications of ultrasounds in nuclear power plants including water detection in dry cask storage, defect detection in reactors, and health monitoring of radiation detectors.

Giant Magnetoresistance Sensors for Aircraft Inspection

Building sensor systems for reliable detection of fatigue cracks in multilayered aircraft fuselage.

Eddy Current Inspection Autoanalysis of Steam Generator Tubes in Nuclear Power Plants

Building signal processing and machine learning pipelines for defect detection and classification within steam generator tubes.

Wireless Senor Networks for Structural Health Monitoring

Building hardware interfaces for integrating ultrasound guided waves sensors with wireless sensors.

Recent Publications

Investigations of degradation and encapsulation of plastic scintillator
Richard T.Kouzes, Herman M.Cho, Christian C.Cowles, Gerges Dib, Paul E. Keller, John E.Smart, Philip J.Smith, Brian J.Tucker, Patrick L.Feng, Nicholas R. Myllenbeck, Stephen Payne
Project DOI
In-situ fatigue monitoring procedure using nonlinear ultrasonic surface waves considering the nonlinear effects in the measurement system
Gerges Dib, Surajit Roy, Pradeep Ramuhalli, Jangbom Chai
PDF Project DOI
Ultrasound Modeling and Simulation: Status Update
Gerges Dib, Michael R Larche, Matthew S Prowant, Richard E Jacob, Pradeep Ramuhalli, Aaron A Diaz
PDF Project
Ensembles of novelty detection classifiers for structural health monitoring using guided waves
Gerges Dib, Oleksii Karpenko, Ermias Koricho, Anton Khomenko, Mahmoodul Haq, Lalita Udpa
PDF Code Project DOI
See all publications