16
Continuous latent variables
dlfc_notes
Preface
1
The Deep Learning Revolution
2
Probabilities
3
Standard distributions
4
Single layer networks: regression
5
Single layer networks: classification
6
Deep Neural Networks
7
Gradient Descent
8
Backpropagation
9
Regularisation
10
Convolutional networks
11
structured distributions
12
Transformers
13
Graph neural networks
14
Sampling
15
Discrete latent variables
16
Continuous latent variables
17
Generative adversarial networks
18
Normalizing Flows
19
Autoencoders
20
Diffusion Models
References
Table of contents
16.1
Principle conponent analysis
16.1.1
Maximum variance formulation
16.1.2
Minimum error formulation
16.1.3
Data compression
16.1.4
Data whitening
16.1.5
High dimensional data
16.2
Probabilistic latent variables
16.2.1
Generative method
16.2.2
Likelihood function
16.2.3
Maximum likelihood
16.2.4
Factor analysis (FA)
16.2.5
Independent component analysis (ICA)
16.2.6
Kalman filters
16.3
Evidence lower bound
16.3.1
Expectation maximisation
16.3.2
EM for PCA
16.3.3
EM for FA
16.4
Nonlinear latent variable models
16.4.1
Nonlinear manifolds
16.4.2
Likelihood function
16.4.3
Discrete data
16.4.4
Four approaches to generative modeling
16
Continuous latent variables
16.1
Principle conponent analysis
16.1.1
Maximum variance formulation
16.1.2
Minimum error formulation
16.1.3
Data compression
16.1.4
Data whitening
16.1.5
High dimensional data
16.2
Probabilistic latent variables
16.2.1
Generative method
16.2.2
Likelihood function
16.2.3
Maximum likelihood
16.2.4
Factor analysis (FA)
16.2.5
Independent component analysis (ICA)
16.2.6
Kalman filters
16.3
Evidence lower bound
16.3.1
Expectation maximisation
16.3.2
EM for PCA
16.3.3
EM for FA
16.4
Nonlinear latent variable models
16.4.1
Nonlinear manifolds
16.4.2
Likelihood function
16.4.3
Discrete data
16.4.4
Four approaches to generative modeling
15
Discrete latent variables
17
Generative adversarial networks