Lecture
Modern NLP: Classical Language Models
Related lectures (36)
Vision-Language-Action Models: Training and Applications
Delves into training and applications of Vision-Language-Action models, emphasizing large language models' role in robotic control and the transfer of web knowledge. Results from experiments and future research directions are highlighted.
Natural Language Generation: Decoding & Training
Explores challenges in natural language generation, decoding algorithms, training issues, and reward functions.
Random Variables and Expected Value
Introduces random variables, probability distributions, and expected values through practical examples.
Interval Estimation: Method of Moments
Covers the method of moments for estimating parameters and constructing confidence intervals based on empirical moments matching distribution moments.
Quantum Source Coding
Covers entropic notions in quantum sources, Shannon entropy, Von Neumann entropy, and source coding.
Language Models: From Theory to Computation
Explores the mathematics of language models, covering architecture design, pre-training, and fine-tuning, emphasizing the importance of pre-training and fine-tuning for various tasks.
Quantum Random Number Generation
Explores quantum random number generation, discussing the challenges and implementations of generating good randomness using quantum devices.
Fundamental Limits of Gradient-Based Learning
Delves into the fundamental limits of gradient-based learning on neural networks, covering topics such as binomial theorem, exponential series, and moment-generating functions.
Estimation and Confidence Intervals
Explores bias, variance, and confidence intervals in parameter estimation using examples and distributions.
Probability and Statistics
Covers p-quantile, normal approximation, joint distributions, and exponential families in probability and statistics.