본문 바로가기

boostcamp AI tech/boostcamp AI

Autoencoder

728x90

study note of LINK

1. Autoencoder

The Encoder generally uses a series of Dense and/or Convolutional layers to encode an image into a fixed length vector that represents the image a compact form,

while the Decoder uses Dense and/or Convolutional layers to convert the latent representation vector back into that same image or another modified image.

 

Practical applications of an Autoencoder network include:

  • Denoising
  • Image Reconstruction
  • Image Generation
  • Data Compression & Decompression
728x90
반응형

'boostcamp AI tech > boostcamp AI' 카테고리의 다른 글

BPTT for RNN  (0) 2023.08.26
Recurrent Neural Networks  (0) 2023.08.23
Convolutional Neural Network  (0) 2023.08.23
Cost functions and Gradient descent  (0) 2023.08.17
Why do we need activation function?  (0) 2023.08.16