Lexicons, n-grams and Language Models

Related lectures (27)

Page 2 of 3

Explores joint random variables, conditional density, and independence in probability and statistics.

Introduces the basics of finite automata, including deterministic and non-deterministic types, regular expressions, and acceptance criteria.

Covers state space models and the expressivity of transformers in sequence copying tasks.

Explores the strong convergence of random variables and the normal distribution approximation in probability and statistics.

Introduces key concepts in probability and random variables, covering statistics, distributions, and covariance.

Explores conditional probability, Bayes' theorem, and prediction decomposition for informed decision-making.

Covers p-quantile, normal approximation, joint distributions, and exponential families in probability and statistics.

Covers the fundamentals of regular expressions and includes exercises on defining languages.

Explores bias, variance, unbiased estimators, and confidence intervals in statistical estimation.

Explains confidence intervals, parameter estimation methods, and the central limit theorem in statistical inference.