Auto-encoders are widely used and maybe even more used than GANs (in fact, auto-encoders are older than GANs, although the main general idea behind GANs is quire old). For example, auto-encoders are used in World Models, for drug design (e.g. see this paper) and many other tasks that involve data compression or generation. So, if we train autoencoders, for ...


In fact, autoencoders are used for generative tasks. Have a look at Tutorial on Variational Autoencoders (VAEs). The coolest thing about VAE is that abstract features can be easily amplified or suppressed based on extracted vectors from the latent space. Let's imagine a model trained on MNIST to generate digits. If you take two images of the same digit which ...


I have not come across music labeling algorithms but upon a google scholar search, I found a couple of papers that aim to do quite the same task. In general, if you have a labeled dataset then you can take an approach of a general speech recognition model. It should work fine for music labeling too, but you might need to tweak certain parameters.

Only top voted, non community-wiki answers of a minimum length are eligible