📚 Coursework:
1. Designing, Visualizing, and Understanding Deep Neural Networks
[ course website, final project, github ]

Topics Covered:
  • Choice of optimizers (Stochastic Gradient Descent, Adam, Adam with Momentum)
  • Convolutional Neural Networks, Skip Connections, Batch Normalization
  • Recurrent Neural Networks
  • Transformers (cross-attention, self-attention, argmax attention), Fine-Tuning, Parameter-Efficient Fine-Tuning/Low Rank Adaptation of LLMs, Model Agnostic Meta Learning
  • Generative Models
2. Natural Language Processing
[ course website, final project, github ]

Topics Covered:
  • Embeddings, Corpora & Annotations
  • Ngram and Log Linear Models
  • Syntax and CFG Parsing
  • Wordnet and Supersenses
  • Part of Speech Tagging
  • In-Context Learning and Prompting (Zero shot, few shot, chain-of-thought)
3. Introduction to Machine Learning
[ course website, github ]

Topics Covered:
  • Support Vector Machines (Hard margin/Soft margin)
  • Gaussian Discriminant Analysis (Linear Discriminant Analysis/Quadratic Discriminant Analysis)
  • Maximum Likelihood Estimation (MLE)
  • Regression: least-squares linear regression, logistic regression, polynomial regression, ridge regression, Lasso
  • Dimensionality reduction: principal components analysis (PCA), random projection
  • Clustering: k-means clustering, hierarchical clustering.
4. Computer Vision
[ course website, final project, github ]

Topics Covered:
  • Image Formation
  • Image Filtering (Convolution, Pyramids, Features, Canonical Basis)
  • Motion Analysis
  • Homography
  • Expectation-Maximization
  • T-Distributed Stochastic Neighboring Embedding
5. Data Engineering [PostgreSQL]
[ course website ]

Topics Covered:
  • Relational Model and Algebra
  • Subqueries
  • Performance Tuning
  • Query Processing and Optimization
  • Data Models
  • Window Functions
  • Semi-structured Data
  • Parallel & Distributed Computing
  • MongoDB
6. Quantitative Research Methods [ R ]

Topics Covered:
  • Experiments
  • Validity & Reliability
  • Randomization
  • Hypothesis Testing
  • Normality Assumption (Shapiro-Wilk test)
  • Correlation (Pearson's coefficient/Spearman's coefficient etc.)
  • Regression
  • p-values
  • t-test
  • Analysis of Covariance (ANOVA)
  • Multivariate analysis of variance (MANOVA)
👨‍🏫 Graduate Student Instructor Roles: