Coursework
Some links may be unavailable due to copyright restrictions.
📚 Selected Coursework at University of Arizona
I am on track to complete my degree in just 2.5 years with a 4.0 GPA and \(6\times\) Academic Highest Distinction (Dean’s list). While we have generous grading policies, I have consistently taken challenging courses, including graduate level courses. Below are some of the most important ones:
CSC 535 – Probabilistic Graphical Models
Bayesian inference, graphical models, EM algorithm, Bayesian deep learning, and variational inference.
Bayesian inference, graphical models, EM algorithm, Bayesian deep learning, and variational inference.
Grade: Ongoing
CSC 577 – Computer Vision
Image formation, camera calibration, shading, photometric stereo, color constancy, edge detection, multiview geometry, homography, RANSAC, segmentation, clustering, recognition, CNNs, autoencoders, tracking, image stitching.
Image formation, camera calibration, shading, photometric stereo, color constancy, edge detection, multiview geometry, homography, RANSAC, segmentation, clustering, recognition, CNNs, autoencoders, tracking, image stitching.
Grade: Ongoing
CSC 545 - Design and Analysis of Algorithms
Asymptotics & recurrences, amortized analysis, randomized algorithms, dynamic programming, greedy, max flow/min cut, approximation algorithms, hashing & Bloom filters, string matching, LCS/edit distance.
Asymptotics & recurrences, amortized analysis, randomized algorithms, dynamic programming, greedy, max flow/min cut, approximation algorithms, hashing & Bloom filters, string matching, LCS/edit distance.
Grade: Ongoing
CSC 453 – Compilers and Systems Software
Lexing, parsing with CFGs and LL1 recursive descent, symbol tables, type checking, ASTs to three-address IR, syntax-directed translation, codegen.
Lexing, parsing with CFGs and LL1 recursive descent, symbol tables, type checking, ASTs to three-address IR, syntax-directed translation, codegen.
Grade: Ongoing
CSC 480/580 – Principles of Machine Learning
Linear and Non-linear models, SVM, Ensemble methods, Markov Chains, PGM, MCMC, LLMs, MDPs, Q-learning, value and policy iterations, DQN.
Linear and Non-linear models, SVM, Ensemble methods, Markov Chains, PGM, MCMC, LLMs, MDPs, Q-learning, value and policy iterations, DQN.
CSC 396 – Deep Learning with Natural Language Processing
Tokenization, GloVe, LSTM, Transformers, LLM finetuning and RAG.
Tokenization, GloVe, LSTM, Transformers, LLM finetuning and RAG.
Grade: A (101.8%)
CSC 345 – Analysis of Discrete Structures
Algorithm analysis, recurrence relations, induction, sorting, hashing, BFS/DFS, topological order in DAGs, MST (Prim/Kruskal), Union & Find, maximum bipartite matching, tries, suffix trees, skiplists, persistent data structures.
Algorithm analysis, recurrence relations, induction, sorting, hashing, BFS/DFS, topological order in DAGs, MST (Prim/Kruskal), Union & Find, maximum bipartite matching, tries, suffix trees, skiplists, persistent data structures.
CSC 296 – Artificial Intelligence
P&NP, Turing Machine, K-means, SVM, Supervised learning, bayes classifier, neural networks, CNN, GNN, PCA/TSNE analysis and applications in CV&NLP.
P&NP, Turing Machine, K-means, SVM, Supervised learning, bayes classifier, neural networks, CNN, GNN, PCA/TSNE analysis and applications in CV&NLP.
CSC 352 – Systems Programming and UNIX
C programming with data structures and pointers, Unix tools and shell scripting.
C programming with data structures and pointers, Unix tools and shell scripting.
Grade: A (97.7%)
CSC 335 – Object-Oriented Programming & Design
Java, Agile, Design Patterns, GUI and software architecture.
Java, Agile, Design Patterns, GUI and software architecture.
CSC 372 – Comparative Programming Languages
(Abstract) Syntax Trees, SML, Prolog, Ruby, type systems, cost models.
(Abstract) Syntax Trees, SML, Prolog, Ruby, type systems, cost models.
Grade: A (100.2%)
CSC 252 – Computer Organization
Assembly programming, machine organization, and processor architecture.
Assembly programming, machine organization, and processor architecture.
Grade: A (98.1%)
MATH 313 – Linear Algebra
Matrix operations, vector spaces, eigenvalues, SVD and applications (e.g. markov chains).
Matrix operations, vector spaces, eigenvalues, SVD and applications (e.g. markov chains).
📘 Self‑Taught Coursework
Outside the university curriculum, I self-studied advanced topics through online platforms like YouTube and Bilibili, skipping unengaging prerequisites to focus on what truly mattered.
Reinforcement Learning
Policy/value iteration, Q-learning, policy gradient, actor-critic, and deep RL with PyTorch. Completed full assignments from the David Silver & UCL course.
Policy/value iteration, Q-learning, policy gradient, actor-critic, and deep RL with PyTorch. Completed full assignments from the David Silver & UCL course.
Resource: UCL Course + Sutton & Barto
Language Modeling from Scratch
Data collection, tokenization, transformer implementation, GPU optimization, scaling laws, pretraining, and alignment with RLHF.
Data collection, tokenization, transformer implementation, GPU optimization, scaling laws, pretraining, and alignment with RLHF.
Resource: Stanford CS336