
Understanding GANs: From Fundamentals to Objective Functions
An in-depth guide to GANs: how two neural networks compete to generate realistic data, the math behind it, and the evolution of objective functions that stabilize training.

An in-depth guide to GANs: how two neural networks compete to generate realistic data, the math behind it, and the evolution of objective functions that stabilize training.

A Haskell reimplementation of FFTW’s genfft metaprogram, generating straight-line optimized C kernels for FFTs via a symbolic DAG and algebraic simplification.

A scraper and recursive backtracking search over Drexel’s Term Master Schedule, enumerating every course schedule that satisfies a set of hard and soft constraints.