variational autoencoders
Variational autoencoders (VAEs) are a type of artificial neural network that learn to generate new data by compressing and decompressing it. They use both an encoder and a decoder network, and add a probabilistic element to the process. VAEs are capable of generating new data samples similar to the training data, allowing for the exploration of the underlying data distribution.
Requires login.
Related Concepts (1)
Similar Concepts
- adversarial autoencoders
- autoencoder layers
- autoencoders
- convolutional neural networks
- encoder-decoder architecture
- fractal encoding
- generative adversarial networks
- generative adversarial networks (gan)
- generative adversarial networks (gans)
- neural network architectures
- neural network models
- recurrent neural networks
- self-affine structures
- variants of gradient descent algorithms
- variational inference