North Carolina State University

North Carolina State University

Master of Science in Electrical Engineering @ NC State University, Raleigh, NC

August 2022 - May 2024

GPA: 3.92/4.00

Relevant Coursework

ECE 514 - Random Processes

Probability theory, random variables, and random processes, Bayes rule, Markov and Poisson processes, joint-marginal and conditional densities, autocorrelation, cross-correlation, linear and non-linear transformations, least-square estimation, Mote Carlo simulations

ECE 558 - Digital Imaging Systems

Image Formation: Modalities, Sensing, Human Vision System, and Models, color fundamentals and color space, Histogram Processing, Spatial Filtering: Convolution, Smoothing, Sharpening, Frequency Domain analysis, Image restoration, Template Matching and Image Pyramid, Edge Detection, Line Segment Detection, Fitting Parametric Models, Harris Corner Detection, SIFT: Key point Detection and descriptor, Image classification

ECE 591 - Data Analytics for Power Systems

Statistical Learning, Confidence Interval and Hypothesis testing, load profile analytics, EDA, Load forecasting, Linear Regression, Decision Trees, Ensemble Learning, Convex Optimization, Gurobi Optimization, Support Vector Machines, Principal Component Analysis, Clustering Methods, Big Data Applications, FCNNs, Regularization Methods, CNNs, RNNs

ECE 542 - Neural Networks and Deep Learning

ML introduction, Probability Theory, Model Selection and Evaluation, Vector Calculus and Optimization, Forward and Backward propagation, Optimization Schemes, Loss and Regularization, Universal Approximation Theorem, Convolutional Neural Networks(CNNs), Recurrent Neural Networks (RNNs), Audio Classification, Dropout and Batch Normalization, Adversarial Learning, Auto Encoders, Generative Adversarial Networks (GANs), VAEs, WGANs, Transformers, Bayesian Neural Networks

CSC 517 - Object Oriented Design and Development

Design of object-oriented systems, using SOLID principles such as the GRASP principles, and methodologies such as CRC cards and the Unified Modeling Language (UML), Software Design patterns, Requirements analysis, Agile Methodology, Static vs. dynamic typing, Metaprogramming, Open-source development practices and tools - refactoring and reimplementation, Test-first development, contributions to an open-source software project.

ECE 791 - Advanced Machine Learning

Linear, Non-linear modeling for inference and decision making, Task Learning, Pac-learning, Artificial Neural Networks (ANNs), CNNs, RNNs, LSTMs, Generalization and Latent Learning: Meta-Learning, AutoEncoders and VAE, Domain Adaptation, Energy Based Learning: Volterra NNs, Generative Models: GANs, Normalizing Flows, Diffusion Model concept, Bayesian Neural Networks, Attention and Transformers Neural Networks, Graph Neural Networks, Graph Attention Networks

CSC 547 - Cloud Computing

Cloud Computing basics and job roles, Datacenter Fundamentals: Microservice implementations, Tenants, Cloud Computing Analysis: IaaS, SaaS, PaaS, FaaS, private-public-multicloud, Cloud Architecture requirements, principles and practices: BRs, TRs, Cloud migration, Load balancing, networking, autoscaling, trade-offs, Cloud automation: automation and orchestration, tools such as Kubernetes, OpenShift, Ansible, nontrivial, lab-based project

CSC 791 - Natural Language Processing

Foundations of NLP, NLP paradigms and techniques, Linguistics and AI, regular expressions, unigrams and n-grams, word embeddings, Part of Speech tagging, Grammar, syntactic and dependency parsing, semantic role labeling, Word Senses, language modeling, sentiment and affect analysis, Information extraction, question answering text-based dialogue, discourse processing, Machine Learning for Language processing: RNNs, LSTMs, GRUs, Attention and Transformers, BERT, LLMs.

CSC 591 - Machine Learning for User Adaptive Systems

Machine Learning introduction, Frequent Pattern Mining, Temporal Sequential Mining, Temporal Pattern Mining, Deep Learning, CNNs, RNNs, LSTMs, GRUs, Dimensionality Reduction, Expectation Maximization (EM), Gaussian Mixture Models (GMMs), GANs, Semi-Supervised Learning, Hidden Markov Models (HMMs), Markov Decision Processes (MDPs), Decision theory, Reinforcement Learning, Deep Reinforcement Learning, Recommendation Systems

ECE 759 - Pattern Recognition (AU)

Statistical Machine Learning, Linear and Non-linear classification, Random variables, Bayes Decision Theory Classification, Discriminant Functions, ML and MAP parameter estimation, Mixture Models, Bayesian Inference, Parzen windows, kNN density estimation and classification, Perceptron algorithm, MMSE and least squares, SVMs, XOR problem, gradient search, backpropagation, Decision trees, Boosting, feature selection, LDA, Structural Risk Minimization, BIC, Feature generation: PCA, SVC, ICA, template matching, Bellman’s principle, Clustering: Proximity measures, sequential, hierarchical, Mixture Decomposition

ECE 763 - Computer Vision

Discriminative and generative modeling and MLE algorithm, Linear and Logistic regression, Mixture models, Kernels and the kernel trick, Factor analysis, Gaussian Process, classification models, Graphical Models, Models for chains and trees - inference: MAP, dynamic programming, MRF-MAP-CRF inference, Temporal Models: Kalman Filter, Particle filtering, Vision Language Models, Image Grammar Models, Probabilistic Models, Deep Learning + Monte Carlo Tree search, Visualizing and understanding CNNs, Computer Vision tools and packages