Generative vs discriminative learning
Create to understand.
1h20 introductory course
What I cannot create, I do not understand - Richard Feynman.
From Naive Bayes
To latent variables and models
Gaussian Mixture Models (GMM)
Theory: Probability review. Bayesian learning.
Hidden Markov Models (HMM)
Latent Dirichlet Allocation (LDA)
Usecase: Melody harmonisation. Ableton. Music.
Variational Auto Encoders (VAE)
VAE can be used to disentangle representations (style vs semantics), and consequently measure similarity between pairs, such as questions.
Summary (models, hypothesis, limits, link with information theory, probabilities, algebra)
Francis Bach. Introduction to Probabilistic Graphical Models. 2018.
Michel Deudon. Learning semantic similarity in a continuous space. Advances in neural information processing systems. vol 31. 2018.