Correct Answer is (i) True
Autoencoders are an unsupervised learning technique in which we leverage neural networks for the task of representation learning. Specifically, we'll design a neural network architecture such that we impose a bottleneck in the network which forces a compressed knowledge representation of the original input.
Autoencoders are trained without supervision. "Autoencoding" is a data compression algorithm where the compression and decompression functions are
a) lossy
b) data-specific
c) learned automatically from examples rather than engineered by a human. Hence Autoencoder are trained without supervision
Additionally, in almost all contexts where the term "autoencoder" is used, the compression and decompression functions are implemented with neural networks.
If the input features were each independent of one another, this compression and subsequent reconstruction would be a very difficult task.
