Genetic Programming with a Genetic Algorithm for Feature Construction and Selection

By Matthew Goble Smith, Larry Bull. 2005

156 citations recorded by the source corpus.

The use of machine learning techniques to automatically analyse data for information is becoming increasingly widespread. In this paper we primarily examine the use of Genetic Programming and a Genetic Algorithm to pre-process data before it is classified using the C4.5 decision tree learning algorithm. Genetic Programming is used to construct new features from those available in the data, a potentially significant process for data mining since it gives consideration to hidden relationships between features. A Genetic Algorithm is used to determine which such features are the most predictive. Using ten well-known datasets we show that our approach, in comparison to C4.5 alone, provides marked improvement in a number of cases. We then examine its use with other well-known machine learning techniques.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Benchmark and Survey of Automated Machine Learning Frameworks (2019, background): “Another popular approach is combining features using genetic programming (Smith and Bull, 2005; Tran et al., 2016).”
Survey on Automated Machine Learning (2019, background): “ion, a random operation is applied to the currently best-performing data set until the performance improvement does converge. Another popular approach is combining features using genetic programming (Smith and Bull, 2005; Tran et al., 2016). Instead of iteratively exploring the transformation tree, ”
Automated Machine Learning: From Principles to Practices (2018, methodology): “…learning configurations, the iterative differentiation methods first iteratively update the model parameter for n steps to obtain 𝑤 𝑛 ( 𝛼 ) for the optimization of lower level objective, and then uses the updated result 𝑤 𝑛 ( 𝛼 ) to approximate ∗ ( 𝛼 ) to obtain the approximated gradient.”
Sentiment Classification using Automatically Extracted Subgraph Features (2010, background): “A lot of work has considered this genetic programming problem (Smith and Bull, 2005).”
Strengthening learning algorithms by feature discovery (2012, methodology): “, plus, minus, multiple, division and modulo), successfully used in [21], performed on the original features.”
A Survey on the Application of Genetic Programming to Classification (2010, background): “A hybrid GP/GA system is presented in [33], where GP is”
AutoLearn — Automated Feature Generation and Selection (2017, methodology): “To overcome this problem, a number of feature learning models have been proposed, such as [6], [7], [8], that use two step batch feature construction to transform the original features.”
Taking Human out of Learning Applications: A Survey on Automated Machine Learning (2018, background): “, greedy search [9] and evolution algorithms [45], [67].”