We provide the first known analytical solution to Word2Vec’s softmax skip-gram objective, introducing the Independent Frequencies Model and deriving a low-cost, training-free method for measuring semantic bias directly from corpus statistics.
Key dimensions that have helped me understand multi-arm bandit problems: action space, problem structure, external information, reward mechanism, and learner feedback.
Discover how NEAT and HyperNEAT changed neuroevolution by automatically designing neural network architectures and scaling them through geometric patterns.
Understand the pattern recognition behind Netflix recommendations, email spam filters, and game-playing AI through three core machine learning approaches.
Explore the building blocks of classic AI reasoning, from knowledge bases and logic to how systems draw new conclusions from existing knowledge.
A fork of Dennis Wilson’s CGP.jl adding the Atari reinforcement-learning experiment layer: experiment variants, fitness functions, and hyperparameter tuning.
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.