An autoencoder is used for image compression and dimensionality reduction. The encoder does the compression of the image and then the decoder decompressed the image from bottleneck. In CNN, when we went through a couple of layers in which one of them is Max Pooling which results in the compression, How this pooling layer is different from encoders because both are having the same functions.
Can we use more than 1 bottleneck in autoencoders?
question from:https://stackoverflow.com/questions/65949441/how-cnn-pooling-layer-is-different-from-encoder-in-autoencoders
