Building an AutoEncoder with Keras
TensorFlow Backend Keras
Resources: https://www.youtube.com/watch?v=uCaPP4blYAg
https://blog.keras.io/building-autoencoders-in-keras.html
To build an autoencoder, you need three things: an encoding function, a decoding function, and a distance function between the amount of information loss between the compressed representation of your data and the decompressed representation (i.e. a "loss" function). The encoder and decoder will be chosen to be parametric functions (typically neural networks), and to be differentiable with respect to the distance function, so the parameters of the encoding/decoding functions can be optimize to minimize the reconstruction loss, using Stochastic Gradient Descent. It's simple! And you don't even need to understand any of these words to start using autoencoders in practice.
One reason why they have attracted so much research and attention is because they have long been thought to be a potential avenue for solving the problem of unsupervised learning, i.e. the learning of useful representations without the need for labels
encoding_dim of 3 means
Instructions: open up command prompt go to cd \PersonalProjects/autoencoder conda activate tensorflow python keras-check.py python test.py conda deactivate