Lectures related to Natural Language Generation: Task

Natural Language Generation: Decoding Techniques and Training Challenges

Covers decoding methods and training challenges in natural language generation.

Natural Language Generation: Decoding & Training

Explores challenges in natural language generation, decoding algorithms, training issues, and reward functions.

Explores sampling a probability distribution and structure functions in statistical analysis.

Covers the implementation of Markov Chain Monte Carlo (MCMC) with the Metropolis algorithm for sampling from posterior distributions.

Max Entropy and Monte Carlo

Explores max entropy, Shannon's entropy, Lagrange multipliers, and Monte Carlo sampling techniques.

Language Models: Fixed-context and Recurrent Neural Networks

Discusses language models, focusing on fixed-context neural models and recurrent neural networks.

Normal Distribution: Characteristics and Examples

Covers the characteristics and importance of the normal distribution, including examples and treatment scenarios.

Generative Models: Self-Attention and Transformers

Covers generative models with a focus on self-attention and transformers, discussing sampling methods and empirical means.

Sampling Theory: Statistics for Mathematicians

Covers the theory of sampling, focusing on statistics for mathematicians.

Boltzmann Machine

Introduces the Boltzmann Machine, covering expectation consistency, data clustering, and probability distribution functions.

Filtering and Sampling of Signals

Explores filtering signals with a moving average filter and the process of sampling, emphasizing the importance of signal reconstruction from samples.

Molecular Dynamics: Sampling and Thermostats

Explores molecular dynamics sampling, conservation laws, energy fluctuations, and various thermostats used for simulations.

Probability Theory: Midterm Solutions

Covers the solutions to the midterm exam of a Probability Theory course, including calculations of probabilities and expectations.

Multivariate Statistics: Normal Distribution

Introduces multivariate statistics, covering normal distribution properties and characteristic functions.

Diffusion Models in Generative Modeling

Explores diffusion models in generative modeling, covering probability estimation, data generation, and model evaluation.

Quantiles, Sampling, Histogram Density

Explores quantiles, sampling, and histogram density for understanding distributions and constructing confidence intervals.

Generative Neural Networks: Sampling and Training

Covers generative neural networks, focusing on sampling, training, and noise addition.

Gaussian Mixture Models & Noisy Signals

Explores Gaussian mixture models and denoising noisy signals using a probabilistic approach.

Review Session: Module 1

Introduces inferential statistics, covering sampling, central tendency, dispersion, histograms, z-scores, and the normal distribution.

Explicit Stabilised Methods: Applications to Bayesian Inverse Problems

Explores explicit stabilised Runge-Kutta methods and their application to Bayesian inverse problems, covering optimization, sampling, and numerical experiments.