<abstract xmlns="http://www.w3.org/1999/xhtml"><p>We propose a method that enables effective code reuse between evolutionary runs that solve a set of related visual learning tasks. We start with introducing a visual learning approach that uses genetic programming individuals to recognize objects. The process of recognition is generative, i.e., requires the learner to restore the shape of the processed object. This method is extended with a code reuse mechanism by introducing a crossbreeding operator that allows importing the genetic material from other evolutionary runs. In the experimental part, we compare the performance of the extended approach to the basic method on a real-world task of handwritten character recognition, and conclude that code reuse leads to better results in terms of fitness and recognition accuracy. Detailed analysis of the crossbred genetic material shows also that code reuse is most profitable when the recognized objects exhibit visual similarity.</p></abstract>

We propose a method that enables effective code reuse between evolutionary runs that solve a set of related visual learning tasks. We start with introducing a visual learning approach that uses genetic programming individuals to recognize objects. The process of recognition is generative, i.e., requires the learner to restore the shape of the processed object. This method is extended with a code reuse mechanism by introducing a crossbreeding operator that allows importing the genetic material from other evolutionary runs. In the experimental part, we compare the performance of the extended approach to the basic method on a real-world task of handwritten character recognition, and conclude that code reuse leads to better results in terms of fitness and recognition accuracy. Detailed analysis of the crossbred genetic material shows also that code reuse is most profitable when the recognized objects exhibit visual similarity.

Cross-task code reuse in genetic programming applied to visual learning

Institute of Computing Science Pozna´n University of Technology, ul. Piotrowo 2, 60-965 Poznań, Poland

International Journal of Applied Mathematics and Computer Science

{"article-title":"Cross-task code reuse in genetic programming applied to visual learning"}

We propose a method that enables effective code reuse between evolutionary runs that solve a set of related visual learning tasks. We start with introducing a...

Cross-task code reuse in genetic programming applied to visual learning

Online veröffentlicht: 25. März 2014

Seitenbereich: 183 - 197

DOI: https://doi.org/10.2478/amcs-2014-0014

Schlüsselwörter
genetic programming, code reuse, knowledge sharing, visual learning, multi-task learning, optical character recognition.

This content is open access.

Cross-task code reuse in genetic programming applied to visual learning

Online veröffentlicht: 25. März 2014

Seitenbereich: 183 - 197

DOI: https://doi.org/10.2478/amcs-2014-0014

Schlüsselwörtergenetic programming, code reuse, knowledge sharing, visual learning, multi-task learning, optical character recognition.

This content is open access.

Schlüsselwörter
genetic programming, code reuse, knowledge sharing, visual learning, multi-task learning, optical character recognition.