Joint Optimization of an Autoencoder for Clustering and Embedding

12/07/2020
by   Ahcène Boubekki, et al.
0

Incorporating k-means-like clustering techniques into (deep) autoencoders constitutes an interesting idea as the clustering may exploit the learned similarities in the embedding to compute a non-linear grouping of data at-hand. Unfortunately, the resulting contributions are often limited by ad-hoc choices, decoupled optimization problems and other issues. We present a theoretically-driven deep clustering approach that does not suffer from these limitations and allows for joint optimization of clustering and embedding. The network in its simplest form is derived from a Gaussian mixture model and can be incorporated seamlessly into deep autoencoders for state-of-the-art performance.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset