ABSTRACT
Traditional genetic programming only supports the use of arithmetic and logical operators on scalar features. The GTMOEP (Georgia Tech Multiple Objective Evolutionary Programming) framework builds upon this by also handling feature vectors, allowing the use of signal processing and machine learning functions as primitives, in addition to the more conventional operators [6]. GTMOEP is a novel method for automated, data-driven algorithm creation, capable of outperforming human derived solutions.
A challenge in this field is working with both large datasets and expensive primitive functions. This paper outlines some of the innovations Zutty et al. have introduced into the GTMOEP framework in order to more efficiently evaluate individuals and tackle new problems. These innovations include: Working with non-feature data, tiered datasets, subtree caches, and initial population creation.
- K. Bache and M. Lichman. UCI machine learning repository, 2013.Google Scholar
- L. Guo, D. Rivero, J. Dorado, C. R. Munteanu, and A. Pazos. Automatic feature extraction using genetic programming: An application to epileptic eeg classification. Expert Systems with Applications, 38(8):10425--10436, 2011. Google ScholarDigital Library
- K. Holladay and K. Robbins. Evolution of signal processing algorithms using vector based genetic programming. In Digital Signal Processing, 2007 15th International Conference on, pages 503--506. IEEE, 2007.Google ScholarCross Ref
- G. Rohling. Multiple objective evolutionary algorithms for independent, computationally expensive objective evaluations. PhD thesis, Georgia Institute of Technology, 2004. Google ScholarDigital Library
- J. Streater. Genetic programming for the automatic construction of features in skin-lesion image classification. Master's thesis, University of Edinburgh, 2010.Google Scholar
- J. Zutty, D. Long, H. Adams, G. Bennett, and C. Baxter. Multiple objective vector-based genetic programming using human-derived primitives. In Proceedings of the 2015 on Genetic and Evolutionary Computation Conference, pages 1127--1134. ACM, 2015. Google ScholarDigital Library
Index Terms
Increasing the Throughput of Expensive Evaluations Through a Vector Based Genetic Programming Framework
Recommendations
Neural network crossover in genetic algorithms using genetic programming
AbstractThe use of genetic algorithms (GAs) to evolve neural network (NN) weights has risen in popularity in recent years, particularly when used together with gradient descent as a mutation operator. However, crossover operators are often omitted from ...
Exact Schema Theory and Markov Chain Models for Genetic Programming and Variable-length Genetic Algorithms with Homologous Crossover
Genetic Programming (GP) homologous crossovers are a group of operators, including GP one-point crossover and GP uniform crossover, where the offspring are created preserving the position of the genetic material taken from the parents. In this paper we ...
Evolving dynamic fitness measures for genetic programming
Highlights- Further research is conducted on dynamic fitness measure genetic programming.
- ...
AbstractThis research builds on the hypothesis that the use of different fitness measures on the different generations of genetic programming (GP) is more effective than the convention of applying the same fitness measure individually ...
Comments