Autoencoding with a Learning Classifier System: Initial Results

Larry Bull

Autoencoding with a Learning Classifier System: Initial Results

Neural and Evolutionary Computing 2019-07-30 v2

Authors: Larry Bull

Abstract

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.

Keywords

deep learning encoder-decoder architecture classification

Cite

@article{arxiv.1907.11554,
  title  = {Autoencoding with a Learning Classifier System: Initial Results},
  author = {Larry Bull},
  journal= {arXiv preprint arXiv:1907.11554},
  year   = {2019}
}

Related papers

View all related →