Graduate-level machine learning course on the current state-of-the-art. Covering topics such as transformers, scaling laws, efficent training, alignment, multimodal models, diffusion models, and much more.
Graduate-level machine learning course examining theoretical ideas and understanding how well they apply in practice. Covering topics such as optimization, generalization, modern architectures, and adversarial attacks.
Linear algebraic foundations of machine learning featuring applications of matrix methods from classification and clustering to denoising and neural networks.
Broad overview of AI focused on knowledge-based search techniques and machine learning methods like neural networks, reinforcement learning, and natural language processing.
Algorithms for computational problems in molecular biology including sequencing, alignment, modeling sequences, phylogenetic trees, and gene expression analysis.
Advanced linear algebra topics like diagonalization, Jordan form, inner product spaces, operators, bilinear forms, matrix norms.
Mathematical analysis of the real number system, sequences, limits, continuity, differentiation, integration, sequences and series of functions.
Proving and understanding the simplex method.
Discrete and continuous-time stochastic processes with applications to queuing, branching, and other models.
Probability distributions, expectation, variance, multivariate probability, Markov’s and Chebyshev’s inequalities, laws of large numbers, central limit theorem.
Partial derivatives, multiple integrals, line and surface integrals.
Deployment (Docker), Networking, SQL Databases (MySQL), HDFS, Spark, Distributed Databases (Cassandra), Kafka, Big Query, Cloud Deployment
Version control, self-balancing trees, unit testing, GUIs, HTML, JavaScript.
Pandas, Matplotlib, search algorithms, web scraping, OOP, machine learning.
Logic, sets, relations, mathematical induction, invariants, algorithm analysis, recurrences, asymptotic growth.