Google Code-in

An Auto-encoder is made up of 3 components:-

1. An Encoder:- The Encoder is nothing but a Neural Network. Basically, the Encoder takes in an input and converts it into a smaller, dense representation.

2. The BottleNeck:- The Bottleneck Layer, with all the panache that naming carries, is nothing but the last layer of the Encoder Network. This is where those smaller, dense representations’ are at.

3. A Decoder:- The Decoder Network does the exact opposite of the Encoder Network. The Encoder Network takes the input image and converts it to a more compressed representation. The Decoder Network, then, takes this compressed representation from the Bottleneck Layer and attempts to reconstruct the original image.

In this task, the student needs to build a simple autoencoder model comprising of two sub-models encoder and decoder resp.

For grading purposes, your model needs to have at least one convolutional layer (i.e. at least 1 Conv layer in each encoder and decoder). We strictly check plagiarism. It should be your own work.