Towards Deep Representation Learning with Genetic Programming
This work addresses representation learning for machine learning practitioners, but it appears incremental as it adapts GP to a known task without demonstrated broad impact.
The authors tackled the problem of transforming large-scale dataset representations into more compact forms using Genetic Programming (GP), developing an autoencoder as a proof of concept and testing it on image datasets, with speculation that iterative use could yield competitive results with state-of-the-art deep neural networks.
Genetic Programming (GP) is an evolutionary algorithm commonly used for machine learning tasks. In this paper we present a method that allows GP to transform the representation of a large-scale machine learning dataset into a more compact representation, by means of processing features from the original representation at individual level. We develop as a proof of concept of this method an autoencoder. We tested a preliminary version of our approach in a variety of well-known machine learning image datasets. We speculate that this method, used in an iterative manner, can produce results competitive with state-of-art deep neural networks.