Autoencoding with a Learning Classifier System: Initial Results
This is an incremental approach to autoencoding for machine learning applications, potentially improving dimensionality reduction methods.
The paper tackled the problem of data dimensionality reduction by introducing a Learning Classifier System (LCS) for autoencoding, building on prior unsupervised clustering work, and found initial results using a neural network representation to be effective.
Autoencoders enable data dimensionality reduction and a key component of many (deep) learning systems. This short paper introduces a form of Holland's Learning Classifier System (LCS) to perform autoencoding building upon a previously presented form of LCS that utilises unsupervised learning for clustering. Initial results using a neural network representation suggest it is an effective approach to reduction.