All Katas - ML Katas

by: newest upvotes saves

Training a Variational Autoencoder (VAE)

this year hard (>1 hr) | loss vae autoencoder generative kl

Implement and train a **Variational Autoencoder (VAE)** on a dataset like MNIST. The encoder should map the input to a latent space distribution (mean and variance), and the decoder should...
Implementing a Simple VAE for Text (Sentence VAE)

this year hard (>1 hr) | rnn vae generative text nlp

Implement a **Variational Autoencoder (VAE)** for text, often called a Sentence VAE. The encoder will be an RNN (e.g., GRU) that outputs a latent distribution, and the decoder will be another RNN...