Smriti Shyamal, Ph.D. - Courses attended

McMaster University, Canada, Sep’13-Apr’18

Data Mining (SEP 6DM3)
W Booth School of Engineering Practice and Technology

Instructor: Dr. Jeff Fortuna, Assistant Professor, Software Engineering Technology
Data descriptions, visualization of data, measurements of data similarity and dissimilarity
K Nearest Neighbors Classification, Bayesian Classifiers, Decision Trees, AdaBoost
Logistic Regression, Support Vector Machine, Neural Networks, Classifier Performance, Unsupervised Learning

Instructor: Dr. Simon Haykin, Distinguished University Professor, Department of Electrical & Computer Engineering
Statistical learning theory, including VC, regularization, and Bayesian theories. Algorithms for multilayer perceptrons, kernel-based learning machines, self-organizing maps, principal components analysis, and blind source separation.
Deep Learning, Recurrent Neural Networks, LSTM, Convolutional Networks, Autoencoders
Sequential state estimation algorithms, including extended Kalman filter, unscented Kalman filter, and particle filters; applications to learning machines.

Instructor: Dr. George Karakostas, Associate Professor, Department of Computing and Software
Binomial heaps, an example of worst-case analysis
Amortized analysis, Fibonacci heaps, an example of amortized analysis
Hash tables, an example of randomized analysis
Greedy algorithms and matroids, Dynamic programming and all-pairs shortest paths, Maximum flow
Linear Programming and Duality, Primal-Dual schema as an algorithmic design tool, NP-completeness, Approximation algorithms

Instructor: Dr. Jeff Fortuna, Assistant Professor, Software Engineering Technology
Statistical Data Analysis, Linear Regression using OLS, MLE and FLD, Linear Classification using the perceptron, neural networks and the SVM, Big Data Architectures.

Instructor: Dr. Kai Huang, Associate Professor, Operations Management
LP and duality; IP and Lagrangian Relaxation
Modeling issues, Basic properties and theory, The value of information and the stochastic solution, Evaluating and approximating expectations
Monte Carlo methods, L-shaped method
Stochastic Integer Programming, Basic properties and theory, Nested decomposition for multi-stage stochastic programming, Finite Horizon Models
Chance constrained programming, Robust optimization

Instructor: Dr. Elkafi Hassini, Professor, Operations Management
Linear, integer and nonlinear programming.
Convexity, duality, Karush-Kuhn-Tucker conditions, non-differentiable optimization, Branch and cut, and decomposition methods (Lagrangian, Bender's and Dantzig-Wolf).
Software implementation issues highlighted via GAMS and its solvers.

Instructor: Dr. Sanzheng Qiao, Department of Computing and Software
Floating-point arithmetic, solutions of systems of linear equations by direct and iterative methods, sparse matrix algorithms, solving systems of nonlinear equations, integration, differentiation, eigenvalue problems, methods for initial value problems in ordinary differential equations, and automatic differentiation.

Instructor: Dr. James (Jim) Reilly, Professor, Department of Electrical & Computer Engineering
Matrix decompositions: eigen-decomposition, QR decomposition, singular value decomposition; solution to systems of equations: Gaussian elimination, Toeplitz systems; least square methods: ordinary, generalized and total least squares, principal component analysis.