Rylan Schaeffer
Resume
Publications
Learning
Blog
Teaching
Jokes
Kernel Papers
Learning
Personal notes on various topics, intended as a learning opportunity and quick reference. Many notes are woefully incomplete. Don't judge :)
Filter by Tag
AI Awakening
Reflections on AI consciousness and awakening.
Approximations and Miscellaneous
Useful approximations, techniques, and miscellaneous mathematical tools.
Associative Memory
Hopfield networks, modern Hopfield models, and memory systems in neural networks.
Bayesian Nonparametrics
Infinite-dimensional probabilistic models including Dirichlet processes, Gaussian processes, and related constructions.
Bayesian Optimization
Sequential optimization of expensive black-box functions using probabilistic surrogate models.
Book Summaries
Personal summaries of books I've read.
Calculus
Differential and integral calculus fundamentals.
Computer Graphics
Rendering, shading, and visual computing techniques.
Convex Analysis
Convex sets, functions, and their properties.
Deep Learning
Neural network architectures, optimization, and training techniques.
Differential Equations
Ordinary and partial differential equations, their solutions and applications.
Entrepreneurship and Venture Capital
Notes on startups, venture capital, and entrepreneurship.
Functional Analysis
Infinite-dimensional vector spaces, operators, and their applications.
Generative Modeling
VAEs, GANs, diffusion models, and other generative approaches.
Inequalities
Important mathematical inequalities and their applications.
Information Theory
Entropy, mutual information, coding theory, and information-theoretic concepts.
Kernel Methods
Reproducing kernel Hilbert spaces and kernel-based machine learning algorithms.
Linear Algebra
Vector spaces, matrices, eigenvalues, and linear transformations.
Machine Learning
Supervised, unsupervised, and general machine learning methods.
Natural Language Processing
Language models, text processing, and computational linguistics.
Neural Computation
Computational models of neural systems and brain function.
Optimization
Convex and non-convex optimization methods.
Probabilistic Graphical Models
Bayesian networks, Markov random fields, and inference algorithms.
Probability
Probability theory, distributions, and random variables.
Programming Languages
Notes on various programming languages and their features.
Randomized Algorithms
Algorithms that use randomness for efficiency or simplicity.
Real Analysis
Foundations of real analysis including limits, continuity, and differentiation.
Reinforcement Learning
Value-based, policy-based, and actor-critic methods for sequential decision making.
Self-Supervised Learning
Contrastive learning, masked prediction, and other self-supervised approaches.
Series
Infinite series, convergence, and summation techniques.
Signals
Signal processing and Fourier analysis.
Statistical Learning Theory
Theoretical foundations of machine learning including VC dimension and generalization bounds.
Statistical Mechanics
Statistical physics concepts and their connections to machine learning.
Statistics
Statistical inference, estimation, and hypothesis testing.
Stochastic Processes
Random processes including Markov chains, martingales, and Brownian motion.
Theory of Computation
Automata theory, computability, and complexity.