NEJul 26, 2019

Autoencoding with a Learning Classifier System: Initial Results

arXiv:1907.11554v23 citations
AI Analysis

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes