Image Feature Learning with Genetic Programming

Ruberto, Stefano; Terragni, Valerio; Moore, Jason H.

doi:10.1007/978-3-030-58115-2_5

Cited by 8 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Genetic Programming for Feature Learning (GPFL) is an AE-like approach to feature learning using GP [20]. Feature learning is a tangential task to NLDR that involves learning representations of image data.…”

Section: Genetic Programming For Autoencodingmentioning

confidence: 99%

A Genetic Programming Encoder for Increasing Autoencoder Interpretability

Schofield¹,

Slyfield²,

Lensen³

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Autoencoders are powerful models for non-linear dimensionality reduction. However, their neural network structure makes it difficult to interpret how the high dimensional features relate to the lowdimensional embedding, which is an issue in applications where explainability is important. There have been attempts to replace both the neural network components in autoencoders with interpretable genetic programming (GP) models. However, for the purposes of interpretable dimensionality reduction, we observe that replacing only the encoder with GP is sufficient. In this work, we propose the Genetic Programming Encoder for Autoencoding (GPE-AE). GPE-AE uses a multi-tree GP individual as an encoder, while retaining the neural network decoder. We demonstrate that GPE-AE is a competitive non-linear dimensionality reduction technique compared to conventional autoencoders and a GP based method that does not use an autoencoder structure. As visualisation is a common goal for dimensionality reduction, we also evaluate the quality of visualisations produced by our method, and highlight the value of functional mappings by demonstrating insights that can be gained from interpreting the GP encoders.

show abstract

Section: Genetic Programming For Autoencodingmentioning

confidence: 99%

A Genetic Programming Encoder for Increasing Autoencoder Interpretability

Schofield¹,

Slyfield²,

Lensen³

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…There has been relevant work on using GP specifically for interpretable visualisation models, which is essentially twodimensional manifold learning [16]. The use of GP for various techniques tangential to manifold learning has also been investigated, such as for auto-encoding [17] and feature learning [18]. Some work has been done into adapting UMAP to produce functional mappings, such as Parametric UMAP [19].…”

Section: Related Workmentioning

confidence: 99%

Using Genetic Programming to Find Functional Mappings for UMAP Embeddings

Schofield

Lensen

2021

2021 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

Manifold learning is a widely used technique for reducing the dimensionality of complex data to make it more understandable and more efficient to work with. However, current state-of-the-art manifold learning techniques -such as Uniform Manifold Approximation and Projection (UMAP) -have a critical limitation. They do not provide a functional mapping from the higher dimensional space to the lower-dimensional space, instead, they produce only the lower-dimensional embedding. This means they are "black-boxes" that cannot be used in domains where explainability is paramount. Recently, there has been work on using genetic programming to perform manifold learning with functional mappings (represented by tree/s), however, these methods are limited in their performance compared to UMAP. To address this, in this work we propose utilising UMAP to create functional mappings with genetic programming-based manifold learning. We compare two different approaches: one that uses the embedding produced by UMAP as the target for the functional mapping; and the other which directly optimises the UMAP cost function by using it as the fitness function. Experimental results reinforce the value of producing a functional mapping and show promising performance compared to UMAP. Additionally, we visualise two-dimensional embeddings produced by our technique compared to UMAP to further analyse the behaviour of each of the algorithms.

show abstract

Evolving Effective Ensembles for Image Classification Using Multi-objective Multi-tree Genetic Programming

Fan

Xue

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Image Feature Learning with Genetic Programming

Cited by 8 publications

References 40 publications

A Genetic Programming Encoder for Increasing Autoencoder Interpretability

A Genetic Programming Encoder for Increasing Autoencoder Interpretability

Using Genetic Programming to Find Functional Mappings for UMAP Embeddings

Evolving Effective Ensembles for Image Classification Using Multi-objective Multi-tree Genetic Programming

Contact Info

Product

Resources

About