Variational Auto-Encoder
Update Log 2021-07-24: Initial Upload Auto-Encoder It is an unsupervised approach for learning a lower-dimensional feature representation from unlabelled training data. The encoder is trained usually with a decoder trying to recover the original data xxx. L2 loss between the reconstructed and original input data is calculated to facilitate the training ..
Read moreHMM
Placeholder
Read more
GAN & Wasserstein GAN
Update Log 2021-07-14: Initial Upload Generative Adversarial Network A generator G and a discriminator D G’s goal: minimise objective such that D(G(z))D(G(z))D(G(z)) is close to 1 (discriminator is fooled into thinking generated G(z)G(z)G(z) is real) D’s goal: maximise objective such that D(x)D(x)D(x) is close to 1 (real) and D(G(z))D(G(z))D(G(z)) is c..
Read more