Write the reparameterization trick z = μ + σ⊙ε

Reparameterization trick

Reparameterization trick enables differentiable sampling for VAE training

Batch normalization

Batch normalization formula: Y = (X - μ) / σ * γ + β

convolution (f * g)(t) = ∫f(τ)g(t-τ)dτ

(f * g)(t) = ∫f(τ)g(t-τ)dτ

Variational autoencoder

ELBO formula in variational inference

Stochastic gradient descent

Policy Gradient Theorem Equation

Gradient descent

Gradient descent weight update equation: w := w - α * ∇J(w)