Project 01

Computational Leaning and Discovery

The course surveys algorithms that enable computers to learn a concept or automatically improve their performance of some task with experience. The main goal of this class is to familiarize students with basic concepts and algorithms of computational learning. Students who complete this course should be able to identify problems where computational learning algorithms can be useful and to apply these algorithms for finding the solution. We discuss the following topics: parametric/non-parametric learning, decision tree learning, neural networks, Bayesian learning, instance-based learning, bias/variance tradeoffs, Vapnik-Chernovenkis theory, support vector machines, and reinforcement learning. The class provides some necessary background introducing basic concepts from statistics, optimization, and information theory, relevant to computational learning. Some popular real world applications of computational learning algorithms are also discussed.

  • Schedule: W 7:20 - 10:00 pm, Robinson Hall B105
  • Office Hours: W 10:00-11:00 pm, Robinson Hall B105
  • Fall 2019

Project 05

The Department of Mathematical Sciences

Department of Mathematical Sciences
4400 University Drive, MS: 3F2
Exploratory Hall, room 4400
Fairfax, Virginia 22030
Phone Number: 703-993-1460
Fax Number: 703-993-1491

<

Project 04

The Center for Simulation and Modelling

Researchers in the Computational Materials Science Center focus on the discovery, interpretation, simulation, and organization of the microscopic interactions between atoms and molecules in condensed phases of materials including biomaterials. The ability to predict materials properties is a fundamental requirement of technological advances and economic competitiveness.

<

Project 03

Linear and Nonlinear Optimization

This book introduces the applications, theory, and algorithms of linear and nonlinear optimization, with an emphasis on the practical aspects of the material. Its unique modular structure provides flexibility to accommodate the varying needs of instructors, students, and practitioners with different levels of sophistication in these topics. The succinct style of this second edition is punctuated with numerous real-life examples and exercises, and the authors include accessible explanations of topics that are not often mentioned in textbooks, such as duality in nonlinear optimization, primal-dual methods for nonlinear optimization, filter methods, and applications such as support vector machines.

  • Coursebook for Graduate Students
  • Publisher: SIAM
  • Year: 2008

About

My research focuses on developing algorithms for nonlinear constrained optimization, their mathematical analysis, efficient implementation and application to problems in science and engineering.

About
  • Location: Northern Virginia
  • Phone: 703 993 4511
  • Email: igriva-at-gmu.edu
  • Address: Dept. of Mathematical Sciences, MS 3F2, Exploratory Hall 4114, GMU, 4400 University Drive, Fairfax, VA 22030, USA
  • Résumé: CV