Teaching & mentorship

I enjoy helping students connect the ideas behind AI with working examples: defining a problem, reasoning through a solution, and testing it in code.

Teaching at UTK

COSC 423/523

Introduction to Artificial Intelligence

Fall 2026 Fall 2025

Rational agents: choosing actions to maximize expected utility.

  • Search & planning

    Represent goals, states, and constraints.

    Uninformed search
    BFS, DFS, uniform-cost search (UCS)
    Informed search
    A*, admissibility, consistency
    Constraint satisfaction (CSP)
    Backtracking, forward checking, arc consistency
    Adversarial search
    Minimax, alpha-beta pruning
  • Uncertainty & decisions

    Reason under uncertainty and over time.

    Probabilistic models
    Bayesian networks, hidden Markov models
    Probabilistic inference
    Conditional independence, Bayesian inference, sampling
    Decision theory
    Utility, expected utility, decision networks
    Markov decision processes (MDPs)
    Bellman equations, value and policy iteration
  • Learning & adaptation

    Learn predictions and policies from experience.

    Reinforcement learning
    Temporal-difference learning, Q-learning
    Supervised learning
    Naive Bayes, perceptron
    Neural networks
    Multi-layer networks for classification

COSC 325

Introduction to Machine Learning

Spring 2026

Learn from data, and test what generalizes to new examples.

  • Models & patterns

    Build predictors and uncover structure in data.

    Supervised learning
    Naive Bayes, perceptron, logistic regression
    Trees & ensembles
    Decision trees, information gain, random forests, AdaBoost
    Clustering
    K-means, hierarchical clustering
    Dimensionality reduction
    PCA, LDA, t-SNE
  • Optimization & evaluation

    Connect training choices to performance on new data.

    Optimization
    Loss functions, gradient descent
    ML pipelines
    Feature engineering; training, validation, and test sets
    Evaluation
    Cross-validation, classification metrics, ROC curves
    Generalization
    Bias-variance trade-off and regularization
  • Neural networks

    Learn representations and relationships in data.

    Network foundations
    Layers, activation functions, learned representations
    Backpropagation
    Gradients and parameter updates
    Attention & transformers
    Self-attention, multi-head attention, positional encoding

Previously a teaching assistant at USC for Data Science: Models and Systems Applications, Cyber-Physical Systems, and Linear Algebra for Engineering.

Research mentorship

At USC, I mentored undergraduate and high-school researchers on neural-operator methods for weather prediction and network analysis of microbial and genetic data. This work included the SURE, CURVE, SHINE, BUGS, and STAR/EHA research programs.